© 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. 6260
    Prev
    Next
    INDEX
    Explanations

    Cyrillic vowels followed by various characters

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

    leet speak, numbers as letters, symbols

    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
     transonic
    0.46
     $)$
    0.44
    潅
    0.44
     buddhav
    0.43
     হুগলী
    0.42
    avacanam
    0.41
     COLLISIONS
    0.41
     টালি
    0.40
    ๗
    0.40
     bosons
    0.40
    POSITIVE LOGITS
    ‎
    0.43
     Ángeles
    0.43
    φε
    0.42
    ਾ
    0.42
     comprised
    0.41
    лиза
    0.41
     ‌
    0.40
    的和
    0.39
    恨
    0.39
     Aguilera
    0.39
    Activations Density 0.016%

    No Known Activations