© 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. 85780
    Prev
    Next
    INDEX
    Explanations

    reply and response actions

    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
    苙
    -1.80
     we
    -1.78
    的所有
    -1.64
     letzte
    -1.61
     و
    -1.59
     και
    -1.55
    ⧠
    -1.52
     и
    -1.52
    なんだろう
    -1.52
     ก็
    -1.50
    POSITIVE LOGITS
    0
    2.13
    赑
    1.91
    d
    1.73
    ing
    1.66
    strator
    1.63
    nologies
    1.53
    ificantly
    1.53
    丨
    1.52
     tjen
    1.52
     valentín
    1.52
    Activations Density 0.002%

    No Known Activations