© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    Why it works

    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
    棿
    3.06
    ا
    2.97
    %$
    2.79
    ు
    2.72
     miserably
    2.68
     работе
    2.60
     Arunachal
    2.59
    u
    2.57
     mercy
    2.56
    та
    2.55
    POSITIVE LOGITS
     mengapa
    3.12
     দর্শ
    2.93
    𝗢
    2.88
    ँ
    2.61
    𝗘
    2.55
     الموج
    2.55
    ें
    2.55
    ع
    2.52
    𝗡
    2.52
    که
    2.47
    Activations Density 0.692%

    No Known Activations