© 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. 207875
    Prev
    Next
    INDEX
    Explanations

    acid, wash, sector

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

    Permitt

    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
     北
    0.50
    CN
    0.49
     giocatori
    0.49
    zoek
    0.48
     giocare
    0.48
     国
    0.48
    国の
    0.47
     खेलने
    0.47
    Č
    0.46
    İK
    0.46
    POSITIVE LOGITS
     جمع
    0.43
    li
    0.43
     స్క
    0.43
    㿟
    0.42
     केमिक
    0.42
     رائ
    0.42
    եր
    0.41
     Pseudo
    0.40
    stash
    0.40
     pseudos
    0.40
    Activations Density 0.001%

    No Known Activations