© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47447
    Prev
    Next
    INDEX
    Explanations

    elevation values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ừ
    -0.87
    尹
    -0.77
    uib
    -0.74
     насеко
    -0.74
    ﾌ
    -0.73
     MALL
    -0.73
     superstructure
    -0.72
    AMILTON
    -0.71
    Descricao
    -0.70
     ذه
    -0.70
    POSITIVE LOGITS
    Initializable
    0.71
     managed
    0.68
    byter
    0.68
     blonde
    0.68
     Sanger
    0.67
     confront
    0.67
    manager
    0.66
     decided
    0.66
    Savannah
    0.66
    bulin
    0.65
    Activations Density 0.043%

    No Known Activations