© 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. 34-GEMMASCOPE-RES-131K
    7. 77667
    Prev
    Next
    INDEX
    Explanations

    license and code changes

    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_34/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
    PRIME
    -0.77
    muscular
    -0.75
     copolymer
    -0.74
    らを
    -0.73
    biological
    -0.73
    hitting
    -0.73
     JUDICIAL
    -0.71
    getResult
    -0.70
    Citation
    -0.70
    пень
    -0.69
    POSITIVE LOGITS
    起こ
    0.82
     Lucky
    0.72
    Scanner
    0.70
     banknotes
    0.69
    Lucky
    0.68
     maus
    0.67
    Cómo
    0.65
     maximization
    0.65
    quias
    0.65
     की
    0.65
    Activations Density 0.072%

    No Known Activations