© 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. 57374
    Prev
    Next
    INDEX
    Explanations

    Claude, bip, Rudolph

    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
    there
    -2.83
    as
    -2.63
    when
    -2.61
    not
    -2.44
     doesn
    -2.42
     bumped
    -2.33
     she
    -2.31
    葙
    -2.31
    re
    -2.30
     sorta
    -2.30
    POSITIVE LOGITS
    s
    3.70
    ’
    3.61
    pecabe
    2.89
     signifikan
    2.63
    цыі
    2.42
    棪
    2.39
    뮐
    2.36
        
    2.34
     teaming
    2.33
    smöglichkeiten
    2.30
    Activations Density 0.003%

    No Known Activations