© 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. 56079
    Prev
    Next
    INDEX
    Explanations

    directly tied or unrelated conversations

    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
    డియో
    0.48
    மையான
    0.48
    浈
    0.44
     कानून
    0.44
     Scholarship
    0.44
     విషయంలో
    0.43
    িন
    0.42
     inevitably
    0.42
    🏤
    0.42
    僳
    0.41
    POSITIVE LOGITS
     exclusives
    0.49
     moyens
    0.48
     tumors
    0.46
     demons
    0.46
     savag
    0.45
     ayant
    0.45
     moteurs
    0.45
     Tiere
    0.44
     skewers
    0.44
     gutt
    0.44
    Activations Density 0.004%

    No Known Activations