© 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. 46173
    Prev
    Next
    INDEX
    Explanations

    prepositions introducing specific contexts

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

    focuses on, relied on

    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
    至少
    0.48
    总
    0.47
     Tổng
    0.45
    还能
    0.44
    如果你
    0.42
    有机会
    0.42
    顶点
    0.40
     Akt
    0.40
    Ary
    0.40
    薙
    0.40
    POSITIVE LOGITS
    UMP
    0.48
     PLA
    0.47
     CANVAS
    0.47
     FRO
    0.47
     RADI
    0.46
    oom
    0.45
    FLP
    0.45
    :"))
    0.45
    IGH
    0.44
     creemos
    0.43
    Activations Density 0.000%

    No Known Activations