© 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. 41079
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "While"

    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
    ar
    -2.30
    '
    -1.86
     همچنین
    -1.86
     anche
    -1.84
    lo
    -1.73
    <bos>
    -1.72
    lu
    -1.68
     <
    -1.63
     ALSO
    -1.63
    li
    -1.63
    POSITIVE LOGITS
    ༀ
    1.63
     некоторые
    1.60
     μὲν
    1.53
    盌
    1.47
     there
    1.46
    ℬ
    1.46
    bigli
    1.44
     なり
    1.41
     französ
    1.41
    　　——
    1.41
    Activations Density 0.041%

    No Known Activations