© 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. 127282
    Prev
    Next
    INDEX
    Explanations

    interconnected nodes and concepts

    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
    '
    0.51
     a
    0.50
     orijinal
    0.47
     ORIGINAL
    0.46
     Fil
    0.46
     Idee
    0.46
     CAN
    0.45
     Time
    0.44
     Enf
    0.44
     Volumen
    0.44
    POSITIVE LOGITS
    ávají
    0.50
    rm
    0.44
    磯
    0.44
     없다
    0.44
    נם
    0.44
    ኛውም
    0.43
     woodwork
    0.43
    뷁
    0.43
    isection
    0.42
    rmse
    0.42
    Activations Density 0.014%

    No Known Activations