© 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. 40592
    Prev
    Next
    INDEX
    Explanations

    click on image or photo

    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
    ↵↵↵
    -1.29
    他の
    -1.26
    この
    -1.17
    几乎
    -1.13
    每个
    -1.13
    -1.12
    ↵↵
    -1.10
    holde
    -1.09
    ↵
    -1.09
    最も
    -1.09
    POSITIVE LOGITS
     ľah
    1.45
     niebieski
    1.38
     acompañado
    1.38
     it
    1.37
     cuyos
    1.32
     męski
    1.30
     acompañada
    1.28
     svoje
    1.27
     čier
    1.27
     reconocida
    1.27
    Activations Density 0.114%
    No Known Activations