© 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. 65466
    Prev
    Next
    INDEX
    Explanations

    cause

    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
     the
    -2.11
     Decke
    -1.77
    encodeWith
    -1.64
     universidades
    -1.61
    skjaer
    -1.60
     It
    -1.59
    "،
    -1.58
    鉉
    -1.49
     помощью
    -1.48
    为大家
    -1.48
    POSITIVE LOGITS
    s
    2.13
    4
    1.80
    ↵↵
    1.67
     minis
    1.58
    也就
    1.49
     corretamente
    1.49
     hugo
    1.48
     reptile
    1.48
     kush
    1.48
    ut
    1.47
    Activations Density 0.009%

    No Known Activations