© 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. 31-GEMMASCOPE-2-RES-65K
    7. 5803
    Prev
    Next
    INDEX
    Explanations

    levels or order

    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
     कर्मी
    0.36
     beauté
    0.35
     mensen
    0.35
     hospitales
    0.34
     mít
    0.33
    腆
    0.33
     utilisant
    0.33
     impoz
    0.33
     نیرو
    0.33
     ljudi
    0.32
    POSITIVE LOGITS
    および
    0.38
    /
    0.35
    čni
    0.35
     or
    0.34
    sw
    0.33
     &/
    0.33
     (&
    0.33
    mar
    0.32
    only
    0.32
    -,
    0.32
    Activations Density 0.191%

    No Known Activations