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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 87
    Prev
    Next
    INDEX
    Explanations

    ready, open, eager, looking

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

    This neuron primarily detects self‐referential pronouns (especially “I” and “I’m,” and to a lesser extent “you”).

    oai_token-act-pair · o4-miniTriggered 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
    <0x0D>
    0.32
     {
    0.32
     oraz
    0.31
    -
    0.31
     <
    0.31
     -
    0.30
    }
    0.29
     flourished
    0.29
     \
    0.29
     மற்றும்
    0.29
    POSITIVE LOGITS
     afraid
    0.51
     hoping
    0.47
     thankful
    0.46
     amazed
    0.46
     fortunate
    0.45
     unaware
    0.45
     intrigued
    0.44
     overjoyed
    0.44
     unsure
    0.43
     worried
    0.43
    Activations Density 0.948%

    No Known Activations