© 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. 7722
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
    воз
    0.34
     calcular
    0.34
    for
    0.32
     confound
    0.32
     $=
    0.31
    %=
    0.31
    とは
    0.31
    保証
    0.31
     calcul
    0.31
     calcula
    0.31
    POSITIVE LOGITS
     جدید
    0.33
     Christopher
    0.32
     Jacksonville
    0.32
     निर्माण
    0.32
     Dynamic
    0.31
    电力
    0.31
    蒈
    0.31
     Eric
    0.31
     Huxley
    0.31
    shaus
    0.31
    Activations Density 0.197%

    No Known Activations