© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2301
    Prev
    Next
    INDEX
    Explanations

    data field names

    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_40_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
     réseau
    0.42
     gimnas
    0.41
     मनात
    0.41
    ٹ
    0.40
    ަރު
    0.39
     Schwier
    0.39
     peralatan
    0.39
     îng
    0.38
    雩
    0.38
     könnt
    0.38
    POSITIVE LOGITS
     ratio
    0.52
    ).
    0.49
    ),
    0.45
    );
    0.44
     percentage
    0.44
    ().
    0.42
     parameters
    0.41
    参数
    0.41
     bytes
    0.40
     absolute
    0.40
    Activations Density 0.027%

    No Known Activations