© 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. 198736
    Prev
    Next
    INDEX
    Explanations

    Silicate, marketing, unique, returns, kg

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

    minced garlic; Root Purpose

    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
    ového
    0.52
    lük
    0.48
    “[
    0.47
     നിന്നും
    0.46
     AsRef
    0.46
    önt
    0.45
    ittet
    0.43
    ính
    0.43
     Kimura
    0.42
     えっ
    0.42
    POSITIVE LOGITS
    General
    0.51
    ABOUT
    0.50
    F
    0.50
    G
    0.50
    ﻓ
    0.50
    Paying
    0.49
     dosen
    0.49
    gameState
    0.48
    Residents
    0.48
    justify
    0.47
    Activations Density 0.001%

    No Known Activations