© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130338
    Prev
    Next
    INDEX
    Explanations

    javascript, python, php, text fragments

    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
     kolek
    -0.82
    Gele
    -0.81
     confirmer
    -0.81
    Bibliote
    -0.80
     şimdi
    -0.79
    zeichnen
    -0.79
    thalle
    -0.77
    medaille
    -0.77
     traductions
    -0.77
    ナップ
    -0.77
    POSITIVE LOGITS
    ดย
    0.90
     http
    0.88
    http
    0.82
    Sigma
    0.82
     strategic
    0.80
    ㅇ
    0.79
     tersebut
    0.79
    is
    0.78
     Forester
    0.78
    gill
    0.78
    Activations Density 0.006%

    No Known Activations