© 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. 2707
    Prev
    Next
    INDEX
    Explanations

    formal, fun, theories, cartoon, movement

    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
     dilated
    0.37
     current
    0.34
     iconic
    0.34
     primal
    0.34
     Ions
    0.33
    =
    0.32
     clicked
    0.32
     *
    0.32
     mirrored
    0.32
     ephemeral
    0.32
    POSITIVE LOGITS
    甚至
    0.39
    减轻
    0.37
    Commonwealth
    0.34
     даже
    0.32
     डेढ़
    0.32
     круп
    0.32
     menyiapkan
    0.32
     навіть
    0.32
    überküloz
    0.32
    鐪
    0.32
    Activations Density 0.189%

    No Known Activations