© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113981
    Prev
    Next
    INDEX
    Explanations

    UI elements: `control` and `group`

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

    the CSS class "form-group" in HTML code.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered 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
    Negative Logits
     relentless
    -1.80
     แต่
    -1.76
     dwóch
    -1.70
     immense
    -1.69
     fervent
    -1.68
     myriad
    -1.66
     marvelous
    -1.62
     was
    -1.61
     masterful
    -1.60
     exceptional
    -1.59
    POSITIVE LOGITS
    .
    1.80
    cenie
    1.70
     untuk
    1.64
     їх
    1.63
     Quite
    1.61
     coupled
    1.59
    Despite
    1.59
    Even
    1.59
    the
    1.58
     gry
    1.58
    Activations Density 0.001%

    No Known Activations