© 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. 9349
    Prev
    Next
    INDEX
    Explanations

    calling super constructors

    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
     verschillende
    -1.49
     chegada
    -1.46
     různých
    -1.45
    蛱
    -1.42
    และ
    -1.42
    Zubereitung
    -1.38
     __
    -1.38
    gyz
    -1.32
    のお知らせ
    -1.31
    🕗
    -1.31
    POSITIVE LOGITS
     (
    1.46
    (
    1.33
    0
    1.27
    ,
    1.23
    .
    1.17
    He
    1.16
    –
    1.13
     الكهرب
    1.12
    e
    1.10
    *
    1.09
    Activations Density 0.001%

    No Known Activations