© 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. 13381
    Prev
    Next
    INDEX
    Explanations

    slash-separated concepts or items

    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
    0
    -3.81
    When
    -3.17
    One
    -2.92
    Maybe
    -2.77
    Some
    -2.73
    Only
    -2.70
    <td>
    -2.67
    I
    -2.66
    Being
    -2.66
    Two
    -2.66
    POSITIVE LOGITS
    ᐠ
    3.20
     colegios
    2.64
     was
    2.59
    会の
    2.59
     '
    2.58
    𐬹
    2.56
    苤
    2.52
     usado
    2.47
    饧
    2.36
    𝝈
    2.36
    Activations Density 0.020%

    No Known Activations