© 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. 21657
    Prev
    Next
    INDEX
    Explanations

    Questions and Examples

    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
     such
    -2.09
     (
    -1.38
     that
    -1.34
     the
    -1.16
     тока
    -1.13
    PostMapping
    -1.13
    的一
    -1.13
    이나
    -1.12
    ;%%
    -1.12
    jsxFileName
    -1.11
    POSITIVE LOGITS
    примеча
    1.38
     它
    1.27
     कौन
    1.24
    .
    1.23
    stehen
    1.23
     paixão
    1.23
     dimmed
    1.21
     Ваш
    1.20
    wijze
    1.20
    !);
    1.18
    Activations Density 0.069%

    No Known Activations