© 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. 10-GEMMASCOPE-RES-131K
    7. 112829
    Prev
    Next
    INDEX
    Explanations

    days and months

    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
    𖥧
    -1.75
    fficking
    -1.73
    einander
    -1.70
    惇
    -1.70
    vignon
    -1.69
     icona
    -1.69
     informée
    -1.66
     所以
    -1.63
     також
    -1.63
    Otra
    -1.56
    POSITIVE LOGITS
    of
    1.78
    ll
    1.70
    p
    1.62
    e
    1.62
    (
    1.58
    鷓
    1.58
    The
    1.53
    ↵↵
    1.52
    =\"
    1.51
    on
    1.49
    Activations Density 0.058%

    No Known Activations