© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27638
    Prev
    Next
    INDEX
    Explanations

    and, with, but

    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
     both
    -0.99
     also
    -0.91
     Both
    -0.80
     additional
    -0.76
    /${
    -0.74
     vectors
    -0.73
     Berufs
    -0.72
     `${
    -0.72
     Hochschule
    -0.71
     even
    -0.70
    POSITIVE LOGITS
     gearbeitet
    0.87
     irse
    0.78
     parec
    0.77
     évidemment
    0.76
    regarding
    0.76
     jinak
    0.76
    placing
    0.75
    upol
    0.75
    redu
    0.75
     marchés
    0.75
    Activations Density 0.086%

    No Known Activations