© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113824
    Prev
    Next
    INDEX
    Explanations

    HTML class attributes

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

    CSS class attributes containing positioning or alignment values like "text", "col", "offset", "h", or "pull".

    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
     have
    -2.73
     when
    -2.28
     where
    -2.27
     would
    -2.25
     will
    -2.25
     has
    -2.23
     until
    -2.22
     which
    -2.08
     as
    -2.06
     by
    -1.98
    POSITIVE LOGITS
    鶿
    1.96
     of
    1.74
    out
    1.69
     jezt
    1.67
    9
    1.66
    めちゃくちゃ
    1.64
     discer
    1.63
    quite
    1.63
    2
    1.63
     allerlei
    1.59
    Activations Density 0.003%

    No Known Activations