© 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. 43042
    Prev
    Next
    INDEX
    Explanations

    one ... is

    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
    ⑊
    -1.64
    ᾳ
    -1.61
    狴
    -1.56
    forChild
    -1.55
    鳎
    -1.53
    >-</
    -1.48
    𓁹
    -1.45
    ndash
    -1.45
    ⎔
    -1.44
    鉨
    -1.44
    POSITIVE LOGITS
     is
    2.66
     this
    1.91
     such
    1.69
     would
    1.66
     time
    1.59
     will
    1.55
    :
    1.52
     most
    1.47
     then
    1.45
     of
    1.40
    Activations Density 0.093%

    No Known Activations