© 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. 118870
    Prev
    Next
    INDEX
    Explanations

    directory paths

    np_acts-logits-general · gemini-2.5-flash-lite

    file paths containing the word "Documents".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    berserk
    -1.70
     up
    -1.69
    錚
    -1.66
    tarta
    -1.59
     pozdě
    -1.57
     this
    -1.55
    yaratan
    -1.55
    bjs
    -1.53
    少爷
    -1.52
     my
    -1.50
    POSITIVE LOGITS
    他
    2.09
    it
    1.94
    a
    1.83
    i
    1.80
    m
    1.69
    ar
    1.66
    new
    1.65
    ing
    1.60
    و
    1.52
    It
    1.51
    Activations Density 0.021%

    No Known Activations