© 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. 84323
    Prev
    Next
    INDEX
    Explanations

    current state or present action

    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
     they
    -2.09
    ↵↵
    -1.96
    ).
    -1.90
     ".
    -1.85
    ."
    -1.78
    戾
    -1.69
    '])
    -1.66
     onları
    -1.62
     oplossing
    -1.61
     böyle
    -1.60
    POSITIVE LOGITS
    焢
    1.84
    幛
    1.81
     a
    1.76
     sebagai
    1.73
     chiama
    1.72
    泺
    1.71
     fermer
    1.70
     judicia
    1.69
     another
    1.66
     errado
    1.66
    Activations Density 0.014%

    No Known Activations