© 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. 22-GEMMASCOPE-RES-131K
    7. 26609
    Prev
    Next
    INDEX
    Explanations

    references, notes, location

    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_22/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
     jee
    -0.93
     porno
    -0.93
     casio
    -0.91
    亿美元
    -0.89
     prs
    -0.88
     Sudoku
    -0.88
    ""}
    -0.88
     dandelion
    -0.86
     mwenye
    -0.85
     chanteuse
    -0.85
    POSITIVE LOGITS
     görüntüleri
    0.90
     parte
    0.89
    kii
    0.81
    Finally
    0.80
     вариантов
    0.79
     packet
    0.78
    着一
    0.78
     Landwirtschaft
    0.77
    に入って
    0.77
    ↵↵↵↵↵↵↵
    0.77
    Activations Density 0.007%

    No Known Activations