© 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. 85538
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
     如果
    -2.48
    colgante
    -2.08
    栊
    -2.05
    Recomendaciones
    -1.92
     desbloquear
    -1.88
    蜮
    -1.87
     ソックス
    -1.87
    
    -1.86
    笮
    -1.84
     اين
    -1.83
    POSITIVE LOGITS
     our
    2.63
     this
    2.50
     all
    2.31
     as
    2.25
    ↵
    2.22
    ',
    2.19
     after
    2.16
     from
    2.13
     these
    2.11
    ",
    2.08
    Activations Density 0.003%

    No Known Activations