© 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. 3934
    Prev
    Next
    INDEX
    Explanations

    own possession year application

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

    The neuron fires most strongly on tokens with very large vocabulary‐ID values (i.e. rare or high-index tokens).

    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_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
    미
    0.75
    ć
    0.71
    aj
    0.69
    uw
    0.68
    HID
    0.68
    Fat
    0.68
    oui
    0.68
    AJ
    0.67
    Button
    0.66
    Aj
    0.66
    POSITIVE LOGITS
     alcanza
    0.62
     infek
    0.59
     pengambilan
    0.58
     letteratura
    0.57
     (-\
    0.56
    ,$$
    0.56
     microstructure
    0.55
     patho
    0.55
     listings
    0.55
     getInstance
    0.55
    Activations Density 0.000%

    No Known Activations