© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84635
    Prev
    Next
    INDEX
    Explanations

    facts and issues

    np_acts-logits-general · gemini-2.5-flash-lite

    efforts and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    可以通过
    0.47
    View
    0.44
    [],
    0.43
    オン
    0.42
    ATORY
    0.42
    入力
    0.42
    䒩
    0.41
    డే
    0.41
    А
    0.41
    関連項目
    0.41
    POSITIVE LOGITS
     sogen
    0.44
     Thông
    0.43
     indígenas
    0.43
    ဍ
    0.40
     scrutin
    0.40
     policing
    0.38
     ridiculed
    0.38
     مسلح
    0.38
    xj
    0.38
    zhihu
    0.38
    Activations Density 0.002%

    No Known Activations