Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 477
    Prev
    Next
    INDEX
    Explanations

    and mathematical operators

    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
     అందు
    0.37
    完成
    0.36
     எனப்படும்
    0.35
     অবশ্য
    0.34
    _{-}^{
    0.33
    ड़ों
    0.33
     courtroom
    0.33
    ()=>{
    0.33
     свадь
    0.32
    accus
    0.32
    POSITIVE LOGITS
     and
    0.51
     และ
    0.51
     +
    0.47
     এবং
    0.46
     AND
    0.45
     ਅਤੇ
    0.44
     mutate
    0.42
     thiab
    0.41
     и
    0.41
     transforms
    0.40
    Activations Density 0.112%

    No Known Activations