© 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. 43065
    Prev
    Next
    INDEX
    Explanations

    relay against

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

    synthetic fibers

    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
    吴
    0.61
    คว
    0.53
    طر
    0.52
    吳
    0.51
    ว
    0.50
    プロフィール
    0.49
    mus
    0.49
    )+\
    0.48
    مركز
    0.48
    国王
    0.48
    POSITIVE LOGITS
    delivery
    0.49
    telephone
    0.48
    plural
    0.46
     ailment
    0.45
     DOI
    0.45
     delivery
    0.44
    ﻊ
    0.44
     illness
    0.43
     refuse
    0.43
    date
    0.43
    Activations Density 0.000%

    No Known Activations