© 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. 58666
    Prev
    Next
    INDEX
    Explanations

    self. property access

    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
    ÁRIO
    -1.84
    忡
    -1.76
    yyb
    -1.75
     współpracy
    -1.68
     můžete
    -1.63
     cilindros
    -1.58
     palanca
    -1.58
     umowy
    -1.58
     copiar
    -1.57
     tirantes
    -1.57
    POSITIVE LOGITS
    7
    2.88
    8
    2.80
    5
    2.73
    9
    2.66
    0
    2.63
    1
    2.63
    2
    2.55
    6
    2.48
    In
    2.06
    4
    2.06
    Activations Density 0.004%

    No Known Activations