© 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. 103986
    Prev
    Next
    INDEX
    Explanations

    technical and instructional phrases

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

    technical or formal documentation, particularly metadata headers and structured text formats.

    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
    灩
    -2.59
    卨
    -2.44
    луйста
    -2.41
    ꦸ
    -2.34
    磲
    -2.34
    eração
    -2.34
    涠
    -2.31
    硨
    -2.31
     militer
    -2.31
    ſchen
    -2.31
    POSITIVE LOGITS
     to
    3.44
     The
    3.17
     have
    2.78
     is
    2.53
     be
    2.42
     akin
    2.28
    .’
    2.27
     since
    2.23
     along
    2.09
      
    2.08
    Activations Density 0.000%

    No Known Activations