© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72850
    Prev
    Next
    INDEX
    Explanations

    among the

    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_10/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
     There
    -1.70
     I
    -1.69
    There
    -1.65
    just
    -1.63
     there
    -1.61
     because
    -1.55
    >
    -1.53
     but
    -1.52
     give
    -1.52
    there
    -1.52
    POSITIVE LOGITS
    噲
    1.89
    좆
    1.73
    bildeten
    1.72
     流れ
    1.68
     ſee
    1.67
    standen
    1.67
    crème
    1.66
     passende
    1.66
     traductions
    1.63
    kehren
    1.63
    Activations Density 0.004%

    No Known Activations