© 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. 183349
    Prev
    Next
    INDEX
    Explanations

    County ofgenerate athose accountedearly birdarguing with

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

    Okay, great"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    greek
    0.46
     αντα
    0.45
     επισ
    0.45
     Dividing
    0.44
    
    0.44
     点
    0.43
     χαρακ
    0.42
    polarized
    0.42
    այր
    0.42
     όπως
    0.42
    POSITIVE LOGITS
    ਕ
    0.48
     carga
    0.46
    Dek
    0.46
    Cele
    0.45
    ANG
    0.45
    edia
    0.44
    करे
    0.44
    බන්ධ
    0.44
    Situ
    0.43
    jé
    0.43
    Activations Density 0.000%

    No Known Activations