© 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. 56896
    Prev
    Next
    INDEX
    Explanations

    two, numbers, counting

    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
    et
    0.47
    r
    0.46
    oj
    0.45
    oL
    0.44
    ab
    0.44
    ty
    0.43
    ding
    0.43
     neighbor
    0.42
    ploidy
    0.42
    rg
    0.41
    POSITIVE LOGITS
    وني
    0.51
     ორი
    0.46
     zie
    0.45
     FOB
    0.45
    への
    0.45
    ونی
    0.44
     two
    0.43
    履歴
    0.43
    秘书
    0.43
    줬
    0.43
    Activations Density 0.003%

    No Known Activations