© 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. 22552
    Prev
    Next
    INDEX
    Explanations

    insertions and insets

    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
    .
    -2.28
    }
    -1.98
     имел
    -1.69
     Hinblick
    -1.69
    <td>
    -1.67
    ⸰
    -1.53
     azonban
    -1.51
    стреча
    -1.49
    новь
    -1.45
     видел
    -1.45
    POSITIVE LOGITS
     quando
    2.34
    尨
    1.94
     ‚
    1.70
     όταν
    1.70
    
    1.69
    鐧
    1.63
     ».
    1.62
    越是
    1.61
    身边的
    1.59
     lorsque
    1.59
    Activations Density 0.018%

    No Known Activations