© 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. 211258
    Prev
    Next
    INDEX
    Explanations

    Germany levy

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

    units and measurements

    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
    เริ่ม
    0.50
    ಭ
    0.49
    きっかけ
    0.48
    ジョ
    0.48
    のス
    0.47
    スの
    0.47
    世話
    0.47
    トラ
    0.46
    の為
    0.46
    ヨ
    0.46
    POSITIVE LOGITS
    vester
    0.50
     район
    0.50
     loudspeakers
    0.49
     Heinrich
    0.49
     ১৯৯
    0.48
     mün
    0.48
     -
    0.48
     vett
    0.48
    :
    0.47
     Medical
    0.47
    Activations Density 0.001%

    No Known Activations