© 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. 126228
    Prev
    Next
    INDEX
    Explanations

    phrase 'located' followed by in, at, close

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

    consistent categorization and states

    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
    autoarima
    0.43
    گذ
    0.41
    स्करी
    0.41
    ガラス
    0.40
    パール
    0.40
    翠
    0.40
     anillo
    0.39
    納税
    0.38
    산
    0.38
     کرل
    0.38
    POSITIVE LOGITS
     ngram
    0.52
     ดู
    0.50
     定义
    0.47
     адре
    0.46
    .");
    0.45
     คุณ
    0.45
    .}
    0.44
     пап
    0.44
     выполняется
    0.44
     เพื่อ
    0.44
    Activations Density 0.004%

    No Known Activations