© 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. 69572
    Prev
    Next
    INDEX
    Explanations

    types of entities and conditions

    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
     -
    -1.59
    p
    -1.48
    vation
    -1.47
    ang
    -1.46
    ed
    -1.43
    c
    -1.43
    h
    -1.39
    k
    -1.37
    t
    -1.35
    in
    -1.34
    POSITIVE LOGITS
     and
    1.66
    tapis
    1.66
    vietnam
    1.57
    chico
    1.52
    mazda
    1.47
    comand
    1.46
    krok
    1.44
     a
    1.43
     மற்ற
    1.42
     šo
    1.42
    Activations Density 0.259%

    No Known Activations