© 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. 11557
    Prev
    Next
    INDEX
    Explanations

    volleyball

    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
    今
    2.38
     pilihan
    2.18
     тепер
    2.11
    पहले
    1.95
     대로
    1.94
    -}\
    1.94
     instructed
    1.92
    不然
    1.89
    º
    1.88
     speck
    1.87
    POSITIVE LOGITS
    ু
    3.07
     glm
    3.00
    mist
    2.95
    alities
    2.86
    as
    2.83
    िंग
    2.78
    ो
    2.69
    er
    2.63
    pstmt
    2.61
     sapply
    2.55
    Activations Density 0.003%

    No Known Activations