© 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. 83945
    Prev
    Next
    INDEX
    Explanations

    can i [verb]

    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
    ’
    -2.30
     ‘‘
    -2.13
    {
    -2.05
     

    -1.84
    ’’
    -1.83
    </strong>
    -1.77
    <em>
    -1.74
    —“
    -1.70
    ’,
    -1.68
     caseros
    -1.68
    POSITIVE LOGITS
     que
    1.78
    齟
    1.73
    掬
    1.69
    防水
    1.66
    馍
    1.60
    ortiment
    1.59
     Schweiz
    1.59
    厘米
    1.59
    влений
    1.58
    蹀
    1.57
    Activations Density 0.040%

    No Known Activations