© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185137
    Prev
    Next
    INDEX
    Explanations

    no limit to

    np_acts-logits-general · gemini-2.5-flash-lite

    allowance barely, cache lines, dynamically format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     خم
    0.46
     julg
    0.46
    →</
    0.45
    ง
    0.43
     رأ
    0.42
    最大の
    0.42
     преда
    0.41
     फ
    0.41
     ഉത്സ
    0.41
     darkest
    0.40
    POSITIVE LOGITS
    setcounter
    0.46
    ElapsedTime
    0.43
    🚻
    0.41
    浏览
    0.41
    Delete
    0.40
     GFP
    0.40
     Rashifal
    0.39
     Subdistrict
    0.38
    atlar
    0.38
    estyle
    0.38
    Activations Density 0.001%

    No Known Activations