© 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. 71385
    Prev
    Next
    INDEX
    Explanations

    following arrangement or structure

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

    accepted structures and conventions

    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
    ighton
    0.40
    0.38
     contrasts
    0.38
    蔣
    0.37
    лях
    0.37
     reviews
    0.36
    नोट
    0.36
    рях
    0.36
     cerrar
    0.34
    <0x0D>
    0.34
    POSITIVE LOGITS
     لأن
    0.47
    ธรรมชาติ
    0.46
    を使
    0.45
     क्योंकि
    0.45
     prirod
    0.45
     സമ്
    0.44
    Literatura
    0.44
    𝒖
    0.43
     supremacy
    0.43
     connotation
    0.43
    Activations Density 0.001%

    No Known Activations