© 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. 69280
    Prev
    Next
    INDEX
    Explanations

    code and list separators

    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
     affect
    -0.90
     傳
    -0.84
     affecting
    -0.82
    外部連結
    -0.80
     barrier
    -0.79
     aleación
    -0.78
    zere
    -0.77
     推荐
    -0.76
    來了
    -0.75
     angle
    -0.75
    POSITIVE LOGITS
     ||
    1.03
     =
    0.82
     .
    0.81
     während
    0.79
    Mq
    0.79
    Ϳ
    0.77
    naphthal
    0.77
     quería
    0.77
    vão
    0.74
     masakan
    0.74
    Activations Density 0.058%

    No Known Activations