© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63731
    Prev
    Next
    INDEX
    Explanations

    `/`, `[`, `{:`, `%`

    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_34/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
     those
    -1.95
     what
    -1.75
     because
    -1.71
     when
    -1.57
     numerous
    -1.51
     these
    -1.51
    <bos>
    -1.50
     now
    -1.47
     any
    -1.45
     various
    -1.45
    POSITIVE LOGITS
    '
    1.43
    だけでなく
    1.41
    ні
    1.38
    '.'
    1.38
    Ë
    1.37
     uſ
    1.37
     boî
    1.37
     predominantly
    1.35
    だけではなく
    1.33
     quintessential
    1.33
    Activations Density 0.031%

    No Known Activations