© 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. 10986
    Prev
    Next
    INDEX
    Explanations

    poem and ceramic

    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
    ್
    2.43
    a
    2.40
    ا
    2.32
    া
    2.26
    rint
    2.20
     Deze
    2.15
    ו
    2.08
    ්
    1.92
    ്
    1.92
    aia
    1.91
    POSITIVE LOGITS
    ına
    2.16
    helpful
    1.93
    ourage
    1.86
    ın
    1.75
     pared
    1.75
     molded
    1.71
     ונ
    1.69
    ுகிறது
    1.68
    ensure
    1.64
    وی
    1.63
    Activations Density 0.047%

    No Known Activations