© 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. 10-GEMMASCOPE-RES-131K
    7. 70217
    Prev
    Next
    INDEX
    Explanations

    GUI text fields and dialogs

    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_10/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
     remarkably
    -2.92
    ”
    -2.88
    }
    -2.73
     *
    -2.66
    并没有
    -2.56
     véritable
    -2.56
    v
    -2.53
     was
    -2.52
     strikingly
    -2.50
     {
    -2.48
    POSITIVE LOGITS
    琤
    3.05
    ꒥
    2.56
     seizoen
    2.50
    嵯
    2.48
    しなければ
    2.48
     rozpoczę
    2.47
    哔
    2.41
    したので
    2.36
     августа
    2.34
     ofreci
    2.34
    Activations Density 0.001%

    No Known Activations