© 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. 3834
    Prev
    Next
    INDEX
    Explanations

    data types and variables

    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
     बिना
    0.45
    ᆫ
    0.44
     माहिती
    0.44
    =
    0.44
    ۱۳
    0.40
    gment
    0.39
    '=
    0.39
    ropolitan
    0.39
    blichen
    0.39
    pharmac
    0.39
    POSITIVE LOGITS
     r
    0.61
     tmp
    0.57
     c
    0.56
     k
    0.55
     q
    0.55
     p
    0.54
     my
    0.54
     we
    0.52
    []
    0.52
     temp
    0.52
    Activations Density 0.110%

    No Known Activations