© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9541
    Prev
    Next
    INDEX
    Explanations

    questions, citations, and code snippets

    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_22/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
     at
    -1.33
     sporad
    -1.17
     cheerful
    -1.07
    maked
    -1.02
     facilitating
    -1.00
     noteworthy
    -0.99
     Верхов
    -0.96
     meticulous
    -0.95
    uniqlo
    -0.94
     oddly
    -0.93
    POSITIVE LOGITS
     représentation
    1.15
    either
    1.11
    couldn
    1.08
    different
    1.08
    probably
    1.06
    Either
    1.06
    textbackslash
    1.04
    ί
    1.03
     embraces
    1.03
    also
    1.03
    Activations Density 0.000%

    No Known Activations