© 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. 22-GEMMASCOPE-RES-131K
    7. 15550
    Prev
    Next
    INDEX
    Explanations

    commands and code snippets

    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_22/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
    forKey
    -0.84
    picas
    -0.82
    ittäin
    -0.82
    errno
    -0.77
    šė
    -0.75
    ormous
    -0.75
    锰
    -0.75
    грева
    -0.75
    ElementType
    -0.75
     undersø
    -0.73
    POSITIVE LOGITS
     droid
    0.87
     acompañada
    0.82
     całość
    0.82
    accompag
    0.81
     maș
    0.80
    __))
    0.75
     дене
    0.74
     acoper
    0.73
     conocido
    0.73
     Coca
    0.72
    Activations Density 0.274%

    No Known Activations