© 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. 42326
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers

    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
    0
    -1.99
    gaven
    -1.76
     היתה
    -1.68
    rī
    -1.66
     antichi
    -1.66
    tamaan
    -1.62
    uč
    -1.61
    5
    -1.60
    の方は
    -1.60
    žne
    -1.58
    POSITIVE LOGITS
    瞅
    1.83
    ebly
    1.78
    unno
    1.73
     alcune
    1.68
    yelitis
    1.67
     และ
    1.67
    new
    1.67
     berbagai
    1.65
     And
    1.63
     facendo
    1.63
    Activations Density 0.020%

    No Known Activations