© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84217
    Prev
    Next
    INDEX
    Explanations

    and also

    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
    इटम
    -2.30
     शुर
    -2.13
     &
    -2.02
    鴣
    -1.95
    Ꮸ
    -1.87
    Namun
    -1.79
    んですが
    -1.77
    +,
    -1.75
     színes
    -1.74
    雳
    -1.72
    POSITIVE LOGITS
    ed
    2.08
     a
    2.02
     esclusivamente
    1.98
     perfettamente
    1.91
     the
    1.90
     his
    1.84
     leggermente
    1.83
     ovunque
    1.82
     ovviamente
    1.80
    ly
    1.79
    Activations Density 0.006%

    No Known Activations