© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99123
    Prev
    Next
    INDEX
    Explanations

    temporal changes, patterns, and measures

    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
    璨
    -3.13
    usstsein
    -2.67
    ﮑ
    -2.66
    屛
    -2.61
     WHICH
    -2.56
    Ꞓ
    -2.53
    glades
    -2.52
    ים
    -2.52
    PvB
    -2.50
    梏
    -2.50
    POSITIVE LOGITS
    1
    4.13
    ↵
    3.72
    -
    3.27
    $
    3.09
    <em>
    3.08
    b
    3.03
    6
    3.02
    </em>
    3.00
    e
    3.00
    a
    2.94
    Activations Density 0.006%

    No Known Activations