© 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. 205619
    Prev
    Next
    INDEX
    Explanations

    describing complex situations and relationships

    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
     carinatis
    0.53
    ناوی
    0.49
     результатом
    0.48
     insures
    0.48
    뮐
    0.48
     econometric
    0.47
     conjectured
    0.47
     zespo
    0.47
    renzia
    0.47
    یط
    0.46
    POSITIVE LOGITS
    1
    0.55
    3
    0.55
    +
    0.54
    0.54
    if
    0.53
     les
    0.48
     into
    0.48
    2
    0.47
     le
    0.46
    가
    0.46
    Activations Density 0.002%

    No Known Activations