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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 111432
    Prev
    Next
    INDEX
    Explanations

    pidgin, singlish, multilingual informal speech

    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_40_width_262k_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
    !.
    0.42
    !;
    0.41
     ผม
    0.41
    [];
    0.40
    または
    0.40
     Evet
    0.40
    odora
    0.40
     ವಿರು
    0.39
     Dorey
    0.39
    !,
    0.39
    POSITIVE LOGITS
     हमरे
    0.49
    哋
    0.48
    嗰
    0.47
     kinda
    0.46
     kino
    0.45
     نشوف
    0.44
     dey
    0.44
     लेके
    0.43
    喺
    0.43
     yana
    0.42
    Activations Density 0.005%

    No Known Activations