© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 8644
    Prev
    Next
    INDEX
    Explanations

    arithmetic completion

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ามารถ
    0.54
     élytres
    0.52
    রিদ্র
    0.51
    াইল
    0.49
     hydrolysis
    0.49
    <unused967>
    0.49
    FTWARE
    0.49
    OURCES
    0.48
    ጶ
    0.48
    ব্লিউ
    0.48
    POSITIVE LOGITS
    in
    0.55
    sum
    0.53
     Sum
    0.53
    1
    0.52
    n
    0.52
     total
    0.50
     sum
    0.50
     총
    0.49
     Total
    0.48
     Comb
    0.46
    Activations Density 0.004%

    No Known Activations