© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85600
    Prev
    Next
    INDEX
    Explanations

    stay here or there, copyright notices

    np_acts-logits-general · gemini-2.5-flash-lite

    describing laughter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ’
    0.54
    ۔
    0.51
    <0xD5>
    0.46
    ět
    0.46
    ´
    0.44
    </sup>
    0.43
    。(
    0.43
    '
    0.42
    odt
    0.41
    oriented
    0.41
    POSITIVE LOGITS
     birçok
    0.50
     banyak
    0.48
     বেশকিছু
    0.47
     lama
    0.47
     piy
    0.46
     Barangay
    0.46
     reforzar
    0.44
     увидеть
    0.44
    णाचा
    0.43
     অনেক
    0.43
    Activations Density 0.000%

    No Known Activations