© 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. 27612
    Prev
    Next
    INDEX
    Explanations

    parenthetical examples or explanations

    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
     ，
    0.61
    kách
    0.59
    t
    0.55
    （
    0.55
    ్‌
    0.51
     （
    0.50
    tric
    0.48
    anbul
    0.47
    statusbar
    0.47
    ,​
    0.46
    POSITIVE LOGITS
     siquiera
    0.57
     INCREASE
    0.54
    е
    0.54
     ﺍ
    0.54
    מ
    0.52
    ﻱ
    0.51
    A
    0.50
     типу
    0.50
     in
    0.49
     ৬
    0.48
    Activations Density 0.144%

    No Known Activations