© 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. 34-GEMMASCOPE-RES-131K
    7. 75563
    Prev
    Next
    INDEX
    Explanations

    deviating from normal

    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_34/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
    ος
    -0.77
    ✜
    -0.74
    istible
    -0.73
     最高
    -0.73
    PHONY
    -0.72
     Chara
    -0.70
     rivalry
    -0.70
    rscheinlich
    -0.70
    ]]
    -0.69
     sibling
    -0.69
    POSITIVE LOGITS
     deviation
    5.56
     deviations
    5.16
     deviate
    5.09
     devi
    4.94
     Deviation
    4.63
    deviation
    4.50
    Deviation
    4.28
     departures
    4.09
     departure
    3.95
    devi
    3.73
    Activations Density 0.150%

    No Known Activations