© 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. 36624
    Prev
    Next
    INDEX
    Explanations

    probability, cost, files, standardize

    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
    נה
    0.47
    ້ມ
    0.47
     conceivably
    0.46
    ༨
    0.46
    وسک
    0.45
    тери
    0.45
     radiative
    0.44
     함수의
    0.44
    䪲
    0.43
     جماعه
    0.43
    POSITIVE LOGITS
     nodig
    0.47
    }{
    0.46
     :
    0.45
     By
    0.44
     Co
    0.43
     Ch
    0.43
     भरोसे
    0.43
     -
    0.43
     بع
    0.42
     as
    0.42
    Activations Density 0.002%

    No Known Activations