© 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. 10-GEMMASCOPE-RES-131K
    7. 7576
    Prev
    Next
    INDEX
    Explanations

    R. R

    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_10/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
     by
    -2.14
     "
    -1.81
     That
    -1.75
     
    -1.66
     in
    -1.64
     To
    -1.62
    m
    -1.61
     Bemerkungen
    -1.60
     be
    -1.59
    s
    -1.59
    POSITIVE LOGITS
    컹
    1.80
     メニュー
    1.75
     ferrovia
    1.73
     JULIO
    1.69
     abiye
    1.69
     lucru
    1.68
     JUAN
    1.67
    ूह
    1.67
     japoneses
    1.66
     uſed
    1.66
    Activations Density 0.000%

    No Known Activations