© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93201
    Prev
    Next
    INDEX
    Explanations

    parameter space diagrams

    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
     house
    -1.08
     casero
    -1.01
     office
    -1.01
     THROUGH
    -1.00
     conduire
    -0.99
     relâche
    -0.97
     contribuer
    -0.95
    seven
    -0.94
     spann
    -0.94
     adicion
    -0.93
    POSITIVE LOGITS
     where
    1.11
     their
    1.10
    ㅘ
    1.01
     for
    1.01
    ÑO
    1.00
    gyz
    0.95
     two
    0.94
    licante
    0.94
    ACIONAL
    0.93
    Witaj
    0.93
    Activations Density 0.029%

    No Known Activations