© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58758
    Prev
    Next
    INDEX
    Explanations

    file paths and code constructs

    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
    favourite
    -0.69
    Descripcion
    -0.69
     code
    -0.68
    deco
    -0.68
    onga
    -0.67
    Descr
    -0.66
    Pio
    -0.66
    dutch
    -0.63
    EventType
    -0.63
     Ngoài
    -0.62
    POSITIVE LOGITS
     Brentford
    0.80
    Acti
    0.71
     Ink
    0.71
     Øst
    0.69
    Bud
    0.69
    Cog
    0.69
     ø
    0.68
    GRP
    0.68
    Greene
    0.66
    னி
    0.66
    Activations Density 0.080%

    No Known Activations