© 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. 130771
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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
    Джере
    -0.99
    Volumen
    -0.98
     halus
    -0.94
    Ỵ
    -0.93
     reposer
    -0.93
     передний
    -0.93
    wige
    -0.91
     habló
    -0.91
     personnaliser
    -0.91
    Informações
    -0.90
    POSITIVE LOGITS
     dnia
    0.83
     tristeza
    0.82
    upra
    0.80
     ants
    0.78
     Ausdrücke
    0.76
     powi
    0.76
    wantErr
    0.75
    sara
    0.75
     wieder
    0.73
    ずる
    0.73
    Activations Density 0.047%

    No Known Activations