© 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. 152897
    Prev
    Next
    INDEX
    Explanations

    potentially for you

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

    variable assignments and code blocks

    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
     Exerc
    0.56
    Exerc
    0.54
     Movers
    0.50
     العملية
    0.49
     movers
    0.49
    <td>
    0.48
    Exercises
    0.48
    答
    0.48
    由于
    0.47
    答案
    0.46
    POSITIVE LOGITS
     กัน
    0.51
     เจ
    0.49
     も
    0.49
     logically
    0.46
     circumferential
    0.46
     ము
    0.46
    ées
    0.46
     પણ
    0.45
     мг
    0.45
    เจ
    0.45
    Activations Density 0.000%

    No Known Activations