© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6085
    Prev
    Next
    INDEX
    Explanations

    tables and comparisons

    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_17_width_16k_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
    де
    1.29
    я
    1.16
    a
    1.15
    }"/>
    1.14
     कहानियां
    1.14
     ngờ
    1.09
    ようになる
    1.07
     cộng
    1.07
    ा
    1.07
     পারিত
    1.06
    POSITIVE LOGITS
     flank
    1.01
     rays
    0.89
     tous
    0.88
    0.87
    ra
    0.87
    lah
    0.86
     existing
    0.86
     none
    0.86
     ظ
    0.84
     KAR
    0.83
    Activations Density 0.049%

    No Known Activations