© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104739
    Prev
    Next
    INDEX
    Explanations

    soon after

    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
    ⚋
    -3.08
    ܜ
    -2.86
     única
    -2.73
    ᯾
    -2.70
    噫
    -2.67
    咵
    -2.67
    剽
    -2.66
    跺
    -2.61
    杙
    -2.59
    ).
    -2.52
    POSITIVE LOGITS
    '
    4.06
    that
    3.75
    t
    3.58
    1
    3.28
    2
    3.25
    an
    3.00
    9
    2.88
    7
    2.77
    $
    2.75
    are
    2.73
    Activations Density 0.009%

    No Known Activations