© 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. 10-GEMMASCOPE-RES-131K
    7. 65661
    Prev
    Next
    INDEX
    Explanations

    town in

    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
    咴
    -3.06
    ↵
    -2.58
    where
    -2.41
    which
    -2.22
    也得
    -2.20
    豈
    -2.20
    拶
    -2.16
    ACIÓN
    -2.08
    𞤢
    -1.98
     poniendo
    -1.96
    POSITIVE LOGITS
    I
    2.92
    ↵↵
    2.67
    玊
    2.47
     einigen
    2.38
    enablog
    2.34
    骉
    2.30
    翃
    2.30
    之际
    2.28
     применение
    2.27
    や
    2.19
    Activations Density 0.016%

    No Known Activations