© 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. 11689
    Prev
    Next
    INDEX
    Explanations

    brewed, Legumes, Global lighting, tough membrane, shampoos

    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
    j
    0.79
    it
    0.73
    l
    0.68
    y
    0.68
    ض
    0.66
    n
    0.65
    و
    0.64
    o
    0.63
    d
    0.63
     I
    0.63
    POSITIVE LOGITS
    そのような
    0.63
    ри
    0.62
     shampoos
    0.62
    {
    0.60
    ми
    0.59
     undecided
    0.58
     フ
    0.58
     године
    0.58
     legumes
    0.58
     саме
    0.58
    Activations Density 0.431%

    No Known Activations