© 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. 75624
    Prev
    Next
    INDEX
    Explanations

    cardscontainer

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

    discussing capability and tendencies

    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
     ""),
    0.48
     방정식
    0.47
    旺
    0.44
     internationally
    0.43
     общего
    0.43
    람
    0.43
    спу
    0.43
     neuritis
    0.43
    ﻼ
    0.43
    ᱔
    0.43
    POSITIVE LOGITS
     അയാള
    0.50
    nton
    0.46
     betroffen
    0.45
    lls
    0.45
    骯
    0.45
    alled
    0.44
     lids
    0.44
     an
    0.43
    ev
    0.43
    nd
    0.43
    Activations Density 0.001%

    No Known Activations