© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58091
    Prev
    Next
    INDEX
    Explanations

    descriptive study types

    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
    Negative Logits
    塍
    -2.77
    Ꮉ
    -2.59
    嘥
    -2.42
    驺
    -2.34
    狻
    -2.28
    
    -2.28
    里有
    -2.23
    魮
    -2.22
    苌
    -2.20
    辚
    -2.17
    POSITIVE LOGITS
    For
    3.08
    7
    3.03
    and
    2.98
    0
    2.98
    if
    2.92
    4
    2.91
    When
    2.81
    9
    2.75
    While
    2.69
    5
    2.69
    Activations Density 0.005%

    No Known Activations