© 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. 24-GEMMASCOPE-2-RES-16K
    7. 636
    Prev
    Next
    INDEX
    Explanations

    emotional states

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on emotionally charged descriptors—words that name strong feelings or states of mind.

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

    words describing strong positive emotions or emotional states.

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

    words denoting strong emotional states, especially -ed adjectives describing how someone feels.

    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_24_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
    れば
    0.59
     necessidades
    0.55
     রাখা
    0.54
     attractive
    0.53
     unattractive
    0.52
     keeps
    0.52
     attracts
    0.52
    比如说
    0.52
     needs
    0.51
     perilous
    0.51
    POSITIVE LOGITS
    不已
    0.55
    CRY
    0.54
    USION
    0.54
    COUNT
    0.53
    traj
    0.52
     understandably
    0.52
    indelijk
    0.52
    Aston
    0.52
    😲
    0.52
    ADE
    0.50
    Activations Density 0.000%

    No Known Activations