© 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. 74176
    Prev
    Next
    INDEX
    Explanations

    hard-coded

    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
    缡
    -1.80
    ⤞
    -1.79
    蹰
    -1.77
     версия
    -1.72
     ????
    -1.70
    </h5>
    -1.68
    ༛
    -1.66
    🫃
    -1.66
     اطلع
    -1.65
     cristianos
    -1.65
    POSITIVE LOGITS
    in
    1.96
    end
    1.74
    on
    1.54
     most
    1.51
    に住
    1.42
    ally
    1.41
     some
    1.38
     as
    1.38
    setcounter
    1.32
     primarily
    1.32
    Activations Density 0.021%

    No Known Activations