© 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. 9745
    Prev
    Next
    INDEX
    Explanations

    as described 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
    uttgart
    -1.75
     bobina
    -1.71
     conç
    -1.63
    谕
    -1.52
    ’，
    -1.52
     tormenta
    -1.49
    儼
    -1.48
    はコチラ
    -1.47
    デーション
    -1.46
    嗐
    -1.46
    POSITIVE LOGITS
     refugiados
    1.75
     również
    1.70
    5
    1.67
    s
    1.63
     maupun
    1.59
     These
    1.59
    4
    1.59
     of
    1.58
    0
    1.57
    عدم
    1.56
    Activations Density 0.022%

    No Known Activations