© 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. 2304
    Prev
    Next
    INDEX
    Explanations

    separators: HS, output, service, password, AR

    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
     Перейти
    0.35
     GoObject
    0.31
     유엔
    0.31
     %``
    0.30
     clicked
    0.30
     {-
    0.30
     crawled
    0.30
     xhrObj
    0.30
     Суриков
    0.29
     使っ
    0.29
    POSITIVE LOGITS
    م
    0.52
    ر
    0.51
    u
    0.50
    ي
    0.48
    em
    0.48
    ко
    0.47
    per
    0.46
    i
    0.45
    ون
    0.45
    म
    0.45
    Activations Density 0.347%

    No Known Activations