© 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. 40576
    Prev
    Next
    INDEX
    Explanations

    llvm and close-knit community/family

    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
     \
    -2.53
     psychotic
    -2.13
     каким
    -1.94
     turbulent
    -1.93
     sensual
    -1.92
     medios
    -1.92
    </h6>
    -1.92
    ⁛
    -1.91
    𝄆
    -1.91
     sleek
    -1.91
    POSITIVE LOGITS
    l
    2.83
    ᷆
    2.53
    很難
    2.41
    注意事
    2.38
     Ursache
    2.22
    疍
    2.22
    ."
    2.16
    la
    2.11
    
    2.09
    y
    2.08
    Activations Density 0.003%

    No Known Activations