© 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. 83939
    Prev
    Next
    INDEX
    Explanations

    this is a statement introducer

    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
     tohoto
    -1.49
     этого
    -1.48
     этой
    -1.41
    愀
    -1.41
     této
    -1.41
     autonomie
    -1.35
     този
    -1.34
     HAVING
    -1.30
     thofe
    -1.30
     thoſe
    -1.25
    POSITIVE LOGITS
     a
    2.34
     how
    2.19
     not
    2.02
     an
    2.00
     one
    2.00
     where
    1.93
     what
    1.66
     NOT
    1.57
     just
    1.54
     why
    1.46
    Activations Density 0.070%

    No Known Activations