© 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. 25380
    Prev
    Next
    INDEX
    Explanations

    code tokens after parenthesis

    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
    torch
    -0.96
     every
    -0.93
     celebró
    -0.93
     EVERY
    -0.89
     vänner
    -0.88
    xlarge
    -0.87
     around
    -0.86
     formó
    -0.86
    ಅ
    -0.85
     there
    -0.85
    POSITIVE LOGITS
    “,
    1.00
    '',
    0.98
    ~,
    0.93
     גם
    0.93
    Chloroform
    0.88
    />,
    0.87
    分别是
    0.86
     Andover
    0.85
    ¹,
    0.83
    influenced
    0.82
    Activations Density 0.002%

    No Known Activations