© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2979
    Prev
    Next
    INDEX
    Explanations

    Survey Junkie

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ሚያ
    0.45
    ის
    0.38
    𝗺
    0.36
    שא
    0.36
    Dios
    0.36
    ilmente
    0.35
    GPU
    0.35
     \%)$
    0.34
    ного
    0.34
     흔
    0.34
    POSITIVE LOGITS
     pakistan
    0.54
     july
    0.54
     essay
    0.53
     pinterest
    0.51
     delhi
    0.50
     kerala
    0.50
     indonesia
    0.49
     england
    0.49
     méxico
    0.49
     microsoft
    0.49
    Activations Density 0.001%

    No Known Activations