© 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. 22-GEMMASCOPE-RES-131K
    7. 36580
    Prev
    Next
    INDEX
    Explanations

    privacy notice and consent

    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
     from
    -1.58
    Kval
    -1.34
     with
    -1.21
    Embal
    -1.16
    Aktu
    -1.13
    Примеча
    -1.13
     oficial
    -1.11
     pedras
    -1.09
     but
    -1.08
     gewiß
    -1.07
    POSITIVE LOGITS
     your
    1.75
     you
    1.73
    your
    1.48
    you
    1.41
     utilisées
    1.40
    有時
    1.37
    เรา
    1.27
     You
    1.26
    ímos
    1.23
    ₓ
    1.23
    Activations Density 0.004%

    No Known Activations