© 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. 162857
    Prev
    Next
    INDEX
    Explanations

    arbitrator, liable, supplier, management

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

    identification

    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
    แท
    0.51
    ト
    0.49
    לה
    0.48
    정
    0.47
    ド
    0.47
    크
    0.47
     marcos
    0.46
    フェ
    0.45
    डो
    0.45
    ベント
    0.44
    POSITIVE LOGITS
     ∈
    0.49
     अनुसार
    0.48
     交
    0.47
    on
    0.45
    irió
    0.45
    }{-
    0.44
     आवास
    0.44
    队的
    0.44
     провели
    0.44
     trú
    0.44
    Activations Density 0.000%

    No Known Activations