© 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. 75434
    Prev
    Next
    INDEX
    Explanations

    most beneficial or common

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

    explaining in depth and balance

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ůli
    0.48
    dě
    0.46
    했지만
    0.46
    었어요
    0.46
    놓
    0.45
     тільки
    0.44
    鈽
    0.44
    इसलिए
    0.43
    ată
    0.43
    ља
    0.43
    POSITIVE LOGITS
     பெரும்பாலான
    0.56
     অধিকাংশই
    0.55
    少なくとも
    0.54
    これらの
    0.54
     Presumably
    0.54
     presumably
    0.52
     اکثریت
    0.52
     bunların
    0.51
     অন্তত
    0.51
    ちゃんと
    0.50
    Activations Density 0.003%

    No Known Activations