© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102323
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    np_acts-logits-general · gemini-2.5-flash-lite

    indentation or whitespace at the beginning of lines, particularly in structured documents like code or formatted text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    0
    -2.44
    i
    -2.41
     When
    -2.28
    t
    -2.28
    h
    -2.27
     make
    -2.20
     Using
    -2.17
     to
    -2.16
    </sup>
    -2.11
     *
    -2.06
    POSITIVE LOGITS
    transQ
    2.84
     auffi
    2.78
     mauva
    2.75
    鲠
    2.73
    quelles
    2.73
    槼
    2.72
     baumwolle
    2.72
    卨
    2.69
    튿
    2.66
     书法
    2.63
    Activations Density 0.050%

    No Known Activations