© 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. 41417
    Prev
    Next
    INDEX
    Explanations

    å Å Hå På

    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
    Недостатки
    -3.16
     條
    -3.03
    ଞ
    -2.95
    Важно
    -2.94
    Without
    -2.92
    뿅
    -2.92
    ୌ
    -2.84
    沇
    -2.83
    戬
    -2.73
    𓄹
    -2.73
    POSITIVE LOGITS
    enablog
    2.73
    (
    2.72
    にい
    2.69
     بالإضافة
    2.69
     predominantly
    2.64
    —
    2.64
     renowned
    2.63
     continually
    2.63
     replete
    2.63
     we
    2.58
    Activations Density 0.003%

    No Known Activations