© 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. 235711
    Prev
    Next
    INDEX
    Explanations

    reported trade analyst

    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
     रिंग
    0.46
     ដ
    0.44
     বানিয়ে
    0.44
     ravaged
    0.43
     préférence
    0.43
    rena
    0.43
     শিশুর
    0.43
     anybody
    0.43
     চমৎকার
    0.42
     乗
    0.42
    POSITIVE LOGITS
    ásico
    0.50
    之类的
    0.48
    厮
    0.46
     melee
    0.46
     casework
    0.44
     cannabin
    0.43
    痿
    0.43
    襄
    0.43
     hearsay
    0.43
    货
    0.43
    Activations Density 0.001%

    No Known Activations