© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13379
    Prev
    Next
    INDEX
    Explanations

    programming module

    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_17_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
    🆈
    2.62
    ب
    2.42
    TO
    2.16
    ना
    2.16
    ే
    2.15
    asche
    2.14
    та
    2.10
    ра
    2.06
    ryl
    2.05
    asaki
    2.04
    POSITIVE LOGITS
     complémentaires
    2.89
    ことになる
    2.87
    𝙧
    2.78
    𝙮
    2.76
    𝙩
    2.62
     capazes
    2.55
     omit
    2.46
    tanto
    2.45
     capaz
    2.36
     capaces
    2.32
    Activations Density 0.026%

    No Known Activations