© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30682
    Prev
    Next
    INDEX
    Explanations

    sequential and serial processing

    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
    déric
    -0.69
     solicit
    -0.65
     białym
    -0.65
     Toxicological
    -0.65
    Evange
    -0.65
     sinned
    -0.65
    Freezing
    -0.64
     overcrowded
    -0.63
    لیه
    -0.63
    jecha
    -0.63
    POSITIVE LOGITS
     sequential
    4.38
     serial
    4.03
    Sequential
    3.72
    sequential
    3.69
     Sequential
    3.67
    serial
    3.47
    Serial
    3.30
     Serial
    3.22
     sequentially
    3.16
     последова
    2.94
    Activations Density 0.152%

    No Known Activations