© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60251
    Prev
    Next
    INDEX
    Explanations

    Honda

    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
    乆
    -3.95
    h
    -3.55
    𖥦
    -2.50
    自然的
    -2.47
    rscheinlich
    -2.36
    就
    -2.31
    苼
    -2.30
    ейчас
    -2.30
     sorgt
    -2.25
    si
    -2.23
    POSITIVE LOGITS
    ↵↵
    3.08
    柃
    2.66
    骉
    2.55
    鉭
    2.45
     pouvez
    2.34
     ,‬
    2.27
    ра
    2.27
     concluding
    2.20
    érées
    2.20
     Herausforderung
    2.16
    Activations Density 0.001%

    No Known Activations