© 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. 178580
    Prev
    Next
    INDEX
    Explanations

    foreign scripts and languages

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

    court, loans, attack, adult, D&D, Warhammer

    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
    )
    0.50
     Top
    0.46
     SUV
    0.46
     Bldg
    0.46
     Motorsport
    0.45
     そこ
    0.45
     missile
    0.45
     flagging
    0.44
     -
    0.44
     palsy
    0.43
    POSITIVE LOGITS
    Ϩ
    0.51
    ải
    0.47
    प्ले
    0.46
    私たち
    0.46
    Οι
    0.46
    λαμβ
    0.45
    Alban
    0.45
    𝐠
    0.45
     உருவாக்க
    0.44
    νης
    0.44
    Activations Density 0.001%

    No Known Activations