© 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. 25997
    Prev
    Next
    INDEX
    Explanations

    code blocks and program syntax

    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
    鸡蛋
    -0.98
     vicepresidente
    -0.90
    şk
    -0.90
    LEAN
    -0.86
    Permutation
    -0.85
    klen
    -0.85
     conflic
    -0.83
    辑
    -0.83
    МА
    -0.82
     particuliers
    -0.82
    POSITIVE LOGITS
     then
    1.25
     Then
    1.17
    Then
    1.13
    拿到
    0.94
    然后
    0.92
     procedure
    0.90
     THEN
    0.88
    then
    0.87
     ثم
    0.87
    紝
    0.86
    Activations Density 0.012%

    No Known Activations