© 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. 6589
    Prev
    Next
    INDEX
    Explanations

    dialogue markers or punctuation

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

    The neuron is triggered by floating‐point number tokens (timestamp‐style or other decimal values).

    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
     jungen
    0.78
    𝘩
    0.77
     giovani
    0.76
     !***
    0.76
     jovens
    0.75
     jóvenes
    0.74
     größten
    0.73
     králov
    0.73
    年輕
    0.73
     Formatting
    0.73
    POSITIVE LOGITS
     (
    0.73
    ;
    0.68
    in
    0.60
    /
    0.55
     =>
    0.55
    omas
    0.55
    ?;
    0.55
    ex
    0.54
     thereof
    0.53
    qu
    0.52
    Activations Density 0.005%

    No Known Activations