© 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. 1142
    Prev
    Next
    INDEX
    Explanations

    non-english word components

    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
     breasts
    0.35
     včetně
    0.34
    ="
    0.34
    她说
    0.33
    은
    0.33
     i
    0.32
    ामान्य
    0.32
     brewers
    0.31
    Clothes
    0.31
     emphasize
    0.31
    POSITIVE LOGITS
    д
    0.54
    د
    0.38
    tien
    0.36
    seekg
    0.35
    entwick
    0.34
    sip
    0.34
    ру
    0.34
    ργαν
    0.34
    ى
    0.33
    tand
    0.33
    Activations Density 0.115%

    No Known Activations