© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73951
    Prev
    Next
    INDEX
    Explanations

    Winston or Prediction followed by name/of

    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_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
     on
    -1.81
     give
    -1.70
     in
    -1.66
     when
    -1.64
     or
    -1.64
     with
    -1.62
    </h1>
    -1.59
     gave
    -1.58
     by
    -1.56
     and
    -1.53
    POSITIVE LOGITS
    nargs
    1.95
     recomand
    1.88
     ـ
    1.66
    thenia
    1.61
    properly
    1.61
    apparently
    1.61
     strikingly
    1.59
    尨
    1.59
    違って
    1.59
     vastly
    1.59
    Activations Density 0.001%

    No Known Activations