© 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. 22-GEMMASCOPE-RES-131K
    7. 71024
    Prev
    Next
    INDEX
    Explanations

    min/max range visualization

    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
    newblock
    -1.13
    mainen
    -1.09
    LookAnd
    -1.06
    unno
    -1.03
    lagte
    -1.02
    ModelMap
    -1.00
     磨
    -1.00
    "}";
    -0.98
     profilo
    -0.97
    emplace
    -0.95
    POSITIVE LOGITS
     for
    1.30
    ACKNOWLEDG
    0.91
    textnormal
    0.90
     THEIR
    0.89
     кү
    0.87
     левый
    0.87
    妪
    0.86
    瞩
    0.85
     range
    0.83
     Makes
    0.82
    Activations Density 0.012%

    No Known Activations