© 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-262K
    7. 11144
    Prev
    Next
    INDEX
    Explanations

    lists of items and descriptions

    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_262k_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
     $:=$
    1.53
     $=$
    1.48
    $>$
    1.46
     recru
    1.42
     ditth
    1.34
    ovsk
    1.33
    STTS
    1.33
     গ্রস্থ
    1.31
    😍😍
    1.31
    TextViewStyle
    1.31
    POSITIVE LOGITS
    জনের
    1.10
    ন্দের
    0.97
    प्पी
    0.95
     Пер
    0.93
     tr
    0.93
     Фин
    0.93
     counter
    0.92
    A
    0.91
    -\
    0.90
    counter
    0.90
    Activations Density 0.000%

    No Known Activations