© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2333
    Prev
    Next
    INDEX
    Explanations

    frequency or commonality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     replacing
    0.39
     вместо
    0.38
     comprising
    0.38
     deverá
    0.36
     Replacing
    0.35
    ?.
    0.34
    的用户
    0.34
    %}
    0.34
     deberán
    0.33
     consequently
    0.33
    POSITIVE LOGITS
     عادة
    0.80
     সাধারণত
    0.77
     biasanya
    0.76
     suelen
    0.74
     завжди
    0.70
     suele
    0.68
     обычно
    0.68
     habituellement
    0.65
     usually
    0.64
     notoriously
    0.62
    Activations Density 0.545%

    No Known Activations