© 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. 22-GEMMASCOPE-RES-131K
    7. 40389
    Prev
    Next
    INDEX
    Explanations

    setting titles or names

    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
     aqueles
    -1.08
     Propiedad
    -1.07
     seluruh
    -1.01
     aziende
    -1.00
     who
    -0.98
     Ubicación
    -0.98
    で見る
    -0.98
     Verdad
    -0.96
     from
    -0.95
     Contacto
    -0.95
    POSITIVE LOGITS
    名は
    1.18
     “
    1.12
    亠
    1.09
    ัก
    1.08
    졌
    1.03
     "
    1.02
    keV
    0.98
    ómetros
    0.98
     صن
    0.98
     name
    0.97
    Activations Density 0.017%

    No Known Activations