© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 2405
    Prev
    Next
    INDEX
    Explanations

    clause, limitations, limits, verified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !";
    1.31
     }}$.
    1.27
    !”.
    1.23
    。\
    1.23
    .";
    1.21
    .';
    1.19
    。.
    1.18
    ’।
    1.17
    "/>.
    1.17
    }^{*}$.
    1.15
    POSITIVE LOGITS
     there
    2.25
     it
    1.87
     they
    1.82
     فإن
    1.72
    there
    1.57
     you
    1.56
     thì
    1.48
     these
    1.47
     we
    1.41
     theres
    1.40
    Activations Density 0.382%

    No Known Activations