© 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. 179188
    Prev
    Next
    INDEX
    Explanations

    facts about and gold mining

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

    recommendations and suggestions

    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
    創建
    0.50
    例
    0.49
    ದಿಂದ
    0.47
    NEST
    0.47
     ಯ
    0.47
     我們
    0.47
    ｧ
    0.46
     よ
    0.46
     與
    0.46
    通過
    0.45
    POSITIVE LOGITS
     recomendar
    0.50
    уре
    0.49
    uras
    0.49
     recomend
    0.49
     particuliers
    0.45
    sthe
    0.44
    的想法
    0.44
    al
    0.44
     Sept
    0.44
    ie
    0.43
    Activations Density 0.000%

    No Known Activations