© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2443
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on first-person self-references (especially “I”/“I’m”) often in expressions of personal feeling or excitement.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    first-person pronouns expressing personal emotions or reactions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    first- or second-person statements expressing strong emotions or excitement, often amplified with intensifiers.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    บ่ง
    0.56
     juxt
    0.56
     propensity
    0.55
     tendencies
    0.55
     способны
    0.54
    能够
    0.54
     ability
    0.53
     அமைந்து
    0.52
    ymmetries
    0.52
     tolerances
    0.52
    POSITIVE LOGITS
     distraught
    1.86
     overjoyed
    1.77
     terrified
    1.73
     excited
    1.72
     enraged
    1.70
     bewildered
    1.66
     distressed
    1.66
     panicked
    1.64
     Excited
    1.64
     angry
    1.62
    Activations Density 0.687%

    No Known Activations