© 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. 119731
    Prev
    Next
    INDEX
    Explanations

    astrophysics and cosmology

    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
    辚
    -2.03
    𖤣
    -2.00
    婼
    -1.91
    méno
    -1.84
    enguaje
    -1.84
    Ⴀ
    -1.84
    跸
    -1.81
    盦
    -1.80
     pedras
    -1.77
    慊
    -1.77
    POSITIVE LOGITS
    ”
    1.97
    .
    1.94
    ’
    1.90
    f
    1.89
    C
    1.73
    E
    1.67
    3
    1.67
    *
    1.67
    from
    1.64
    In
    1.63
    Activations Density 0.006%

    No Known Activations