© 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. 31-GEMMASCOPE-2-RES-65K
    7. 45640
    Prev
    Next
    INDEX
    Explanations

    every, per, each, unit, ratio

    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_65k_l0_medium
    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
     않았
    0.39
     சீ
    0.39
     দলের
    0.38
     Está
    0.38
     ஆண்டுகளாக
    0.37
     સમય
    0.37
    ͕
    0.37
     ইতিহাসে
    0.36
     器
    0.36
    esia
    0.35
    POSITIVE LOGITS
     every
    0.58
    마다
    0.50
    ごとに
    0.47
     ogni
    0.46
    Every
    0.46
     unit
    0.45
    每一
    0.45
     equivale
    0.45
     каж
    0.45
     ratio
    0.44
    Activations Density 0.127%

    No Known Activations