© 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
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63276
    Prev
    Next
    INDEX
    Explanations

    Haitian Creole, Vodou, spirits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_width_262k_l0_small_affine
    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
    MathClass
    0.42
    დას
    0.41
     Ug
    0.40
    ◉
    0.39
     виду
    0.38
    вої
    0.37
     afield
    0.37
    臼
    0.36
    嬉
    0.36
     রাখি
    0.36
    POSITIVE LOGITS
    isyen
    0.57
     Haitian
    0.55
    èl
    0.47
     ఇం
    0.43
     Sekret
    0.42
     nou
    0.41
     Creole
    0.41
     Ti
    0.40
     Avril
    0.40
     kom
    0.40
    Activations Density 0.003%

    No Known Activations