© 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. 10-GEMMASCOPE-RES-131K
    4. 61002
    Prev
    Next
    INDEX
    Explanations

    akin to

    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
    </h1>
    -3.39
    *}[
    -2.67
    );
    
    -2.67
    </b>
    -2.58
    ):
    -2.58
     succinct
    -2.50
     мы
    -2.45
    ":
    
    -2.31
     With
    -2.23
    入り口
    -2.23
    POSITIVE LOGITS
    geſ
    2.64
     verhind
    2.59
    acterísticas
    2.48
     begonnen
    2.47
    [
    2.44
     понял
    2.41
    1
    2.34
     aérea
    2.33
     allemand
    2.33
     ersche
    2.31
    Activations Density 0.003%

    No Known Activations