© 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. 85760
    Prev
    Next
    INDEX
    Explanations

    meta-analysis

    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
     &
    -1.95
     and
    -1.81
     in
    -1.76
     jika
    -1.73
     are
    -1.67
     during
    -1.66
     would
    -1.64
     i
    -1.63
     who
    -1.61
     began
    -1.60
    POSITIVE LOGITS
     monstre
    2.11
     mauva
    1.93
    魠
    1.85
     拆
    1.79
     refroid
    1.78
     goû
    1.75
     réve
    1.74
     soigne
    1.73
    ＊＊＊
    1.70
    　＊
    1.68
    Activations Density 0.022%

    No Known Activations