© 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. 74010
    Prev
    Next
    INDEX
    Explanations

    software development and related components

    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
     The
    -1.75
    駡
    -1.52
    transQ
    -1.50
     
    -1.46
     apare
    -1.45
     \
    -1.45
     aprecia
    -1.43
     fourni
    -1.43
     hosped
    -1.38
    ções
    -1.38
    POSITIVE LOGITS
    The
    1.94
    媖
    1.88
    In
    1.84
    .
    1.84
    獃
    1.74
    镚
    1.72
     动物
    1.70
     软件
    1.69
    癭
    1.59
    .”
    1.59
    Activations Density 0.080%

    No Known Activations