© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128434
    Prev
    Next
    INDEX
    Explanations

    caring congregation, revolutionary impact, weeks

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

    levels, titles, arithmetic

    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
    dee
    0.50
    ㏄
    0.47
     dane
    0.46
    iye
    0.45
    zeg
    0.45
     dee
    0.45
     resigned
    0.44
    ast
    0.44
     darbo
    0.44
    bc
    0.43
    POSITIVE LOGITS
    敺
    0.51
    를
    0.50
    полне
    0.49
    тропо
    0.47
    oconvex
    0.45
    🥋
    0.45
     коронави
    0.45
    వైపు
    0.45
    วัด
    0.45
    🆁
    0.45
    Activations Density 0.003%

    No Known Activations