© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1740
    Prev
    Next
    INDEX
    Explanations

    comforting and converting

    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_9_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
    ity
    4.12
    र
    4.02
    an
    3.96
    le
    3.92
    y
    3.84
    ം
    3.51
    ف
    3.51
    er
    3.50
    re
    3.47
    তে
    3.44
    POSITIVE LOGITS
    
    3.20
    ाइ
    3.14
    𝙞
    2.98
    findViewById
    2.97
    𝙚
    2.87
    <unused1149>
    2.78
    ഭ
    2.78
    انية
    2.77
    $)$.
    2.75
     lacking
    2.73
    Activations Density 0.842%

    No Known Activations