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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27452
    Prev
    Next
    INDEX
    Explanations

    encoded or obfuscated text formats such as base64, leetspeak, character substitutions, and compressed notation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @gersonkroiz

    phonetic distortions, leet speak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.21
     and
    0.19
    ↵↵
    0.17
    _
    0.17
     which
    0.16
    ;
    0.16
    +
    0.16
    \
    0.15
     polynomial
    0.15
    x
    0.15
    POSITIVE LOGITS
     финанси
    0.15
     финансо
    0.13
     सेलिब्र
    0.13
     завтра
    0.13
     рассказать
    0.13
    艨
    0.13
    efois
    0.12
    jalan
    0.12
     соціа
    0.12
     демокра
    0.12
    Activations Density 0.000%

    No Known Activations