© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77839
    Prev
    Next
    INDEX
    Explanations

    table tennis blade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     acredit
    0.39
     માત્ર
    0.36
     கடுமையான
    0.34
     പഞ്ചായ
    0.34
     bassist
    0.33
     mantenimiento
    0.31
    ృష్
    0.31
    寛
    0.31
     பயிற்
    0.31
     znacz
    0.31
    POSITIVE LOGITS
     गर्न
    0.36
    ش
    0.35
    وان
    0.35
    ን
    0.35
    ری
    0.34
     (=
    0.34
    หร่
    0.33
    ))
    0.33
    ือก
    0.33
    پ
    0.33
    Activations Density 0.289%

    No Known Activations