© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73569
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas with symbols

    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
    Beskrivning
    -0.85
     transporta
    -0.81
    žne
    -0.79
     actually
    -0.79
    Fuckin
    -0.78
     book
    -0.75
    檚
    -0.75
     transportation
    -0.75
     payment
    -0.73
     definitely
    -0.73
    POSITIVE LOGITS
    ♙
    0.88
    seem
    0.85
    Avoid
    0.84
    why
    0.84
     taches
    0.83
    compared
    0.82
     dividida
    0.82
    minus
    0.82
     boucles
    0.81
    entire
    0.80
    Activations Density 0.042%

    No Known Activations