© 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. 130309
    Prev
    Next
    INDEX
    Explanations

    LLC– Limited Responsibility Company

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

    inhibited by

    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
    ತ್ತು
    0.45
     Ethiop
    0.44
    什么
    0.43
    읍
    0.43
     snork
    0.42
    _
    0.42
     Protestants
    0.41
    ваны
    0.41
    ，
    0.41
    <0x86>
    0.40
    POSITIVE LOGITS
     بیماری
    0.50
     spectroscopic
    0.49
     ی
    0.49
     словарь
    0.48
     multiSelectList
    0.48
    adapted
    0.46
     пери
    0.46
     соло
    0.46
    যখন
    0.46
     なお
    0.46
    Activations Density 0.000%

    No Known Activations