© 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. 78492
    Prev
    Next
    INDEX
    Explanations

    doc followed by document or book

    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
     Remaining
    -0.95
     felicidade
    -0.88
     useAppContext
    -0.88
     vorigen
    -0.88
    hols
    -0.85
     mittleren
    -0.85
    CHREIBUNG
    -0.84
    metik
    -0.84
    Cyfarwyddwr
    -0.84
    VIRGO
    -0.84
    POSITIVE LOGITS
     DOC
    1.53
     Doc
    1.52
    doc
    1.40
     doc
    1.36
    Doc
    1.31
    DOC
    1.24
    umen
    1.23
    document
    1.16
     Document
    1.16
     доку
    1.09
    Activations Density 0.020%

    No Known Activations