© 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. 111043
    Prev
    Next
    INDEX
    Explanations

    states of being

    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
    kovou
    -1.58
    nému
    -1.54
     sebagainya
    -1.52
     altercation
    -1.40
     heridos
    -1.40
    solu
    -1.34
    Variety
    -1.34
    ditto
    -1.33
    varargin
    -1.33
    badan
    -1.33
    POSITIVE LOGITS
    /"
    1.63
     legitimately
    1.56
    アーム
    1.50
    卻
    1.49
    圌
    1.45
     fact
    1.43
     sensibly
    1.41
    :-)
    1.41
     despo
    1.38
     comentário
    1.36
    Activations Density 0.028%

    No Known Activations