© 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. 127594
    Prev
    Next
    INDEX
    Explanations

    iPod and Volkswagen

    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
    1
    -3.86
    7
    -3.52
    4
    -3.36
    5
    -3.31
    3
    -3.28
    6
    -3.22
    0
    -3.20
    8
    -3.16
    9
    -2.81
    橚
    -2.72
    POSITIVE LOGITS
    獃
    3.28
    缡
    2.64
    QUÉ
    2.63
    逦
    2.59
    ꯳
    2.59
    峮
    2.58
     ſou
    2.53
    鈷
    2.50
    櫪
    2.45
    <
    2.44
    Activations Density 0.015%

    No Known Activations