© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26134
    Prev
    Next
    INDEX
    Explanations

    cryptography and -ography suffixes

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

    python code definitions

    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
    Cause
    0.48
     hasn
    0.47
    다
    0.47
    是否有
    0.47
    Temple
    0.46
     temple
    0.45
     storey
    0.45
     Kredit
    0.45
    شارة
    0.45
    ურთი
    0.45
    POSITIVE LOGITS
    モチ
    0.46
     cryptography
    0.44
    ography
    0.44
     Vincenzo
    0.43
     cinéma
    0.43
    ٹس
    0.42
    怵
    0.42
    ici
    0.41
     න
    0.40
    atique
    0.40
    Activations Density 0.000%

    No Known Activations