© 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. 22-GEMMASCOPE-RES-131K
    7. 79609
    Prev
    Next
    INDEX
    Explanations

    non-www, noncomatose, nonscarring

    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_22/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
    ervare
    -1.10
    fø
    -0.93
    mata
    -0.91
    taires
    -0.90
    γμα
    -0.89
    ssa
    -0.85
    anadas
    -0.85
     rather
    -0.84
     иде
    -0.82
    ’;
    -0.82
    POSITIVE LOGITS
     olmayan
    1.37
     وغير
    1.23
     vs
    1.09
    less
    1.00
    かどうか
    0.90
     versus
    0.84
     ones
    0.82
    和其他
    0.81
     less
    0.81
    ḑ
    0.79
    Activations Density 0.271%

    No Known Activations