© 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. 63600
    Prev
    Next
    INDEX
    Explanations

    strict confidence; LinkedIn

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

    'use strict'; and Officers look

    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
    weighted
    0.47
    Weighted
    0.46
    brit
    0.46
    zahl
    0.45
     большин
    0.45
     höch
    0.44
    طار
    0.43
    ˏ
    0.43
    clusters
    0.43
    čet
    0.43
    POSITIVE LOGITS
     Considerando
    0.48
     Harg
    0.47
    िति
    0.47
     Đồng
    0.46
     Bagaimana
    0.46
     對
    0.45
     Năm
    0.45
     Cuando
    0.45
     Cu
    0.45
     Lihat
    0.45
    Activations Density 0.000%

    No Known Activations