© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103840
    Prev
    Next
    INDEX
    Explanations

    bird names and species

    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
    浹
    -1.78
     They
    -1.63
    鄖
    -1.60
     swoich
    -1.59
    擻
    -1.55
     reacties
    -1.52
    También
    -1.48
    鵯
    -1.47
    Also
    -1.43
     bidra
    -1.43
    POSITIVE LOGITS
    is
    1.96
    "
    1.84
    --
    1.78
    '
    1.75
    *
    1.71
    _
    1.68
    ным
    1.45
    ...
    1.43
     has
    1.38
    <th>
    1.37
    Activations Density 0.024%

    No Known Activations