© 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. 1219
    Prev
    Next
    INDEX
    Explanations

    code comments and `public` keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ᴙ
    0.68
     This
    0.65
    McG
    0.65
    This
    0.64
    side
    0.64
    cap
    0.64
    breaking
    0.64
    CD
    0.63
     này
    0.63
    toc
    0.63
    POSITIVE LOGITS
    /***
    0.81
    //#
    0.79
    /**
    0.77
     /**
    0.73
     perverse
    0.73
    /*
    0.73
     paramilitary
    0.73
    ///////////////
    0.71
     aveva
    0.70
     persecution
    0.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.