© 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. 10-GEMMASCOPE-RES-131K
    7. 21935
    Prev
    Next
    INDEX
    Explanations

    notes, docs, charts, logs

    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_10/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
    cobs
    -1.28
     but
    -1.27
     չ
    -1.23
    HAEL
    -1.19
    诟
    -1.16
     because
    -1.14
     most
    -1.13
    .
    -1.12
     eikä
    -1.10
    lifier
    -1.07
    POSITIVE LOGITS
     from
    1.26
     quizá
    1.23
    Números
    1.20
    cnbc
    1.20
     recientemente
    1.20
     Francji
    1.19
     preescolar
    1.16
     publicada
    1.16
     cuyas
    1.10
    suporte
    1.09
    Activations Density 0.220%

    No Known Activations