© 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. 33856
    Prev
    Next
    INDEX
    Explanations

    getting along

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

    lists, anatomy, 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
    acaktır
    0.50
     Amitabh
    0.50
    ဦ
    0.48
     treacher
    0.46
     gracefully
    0.45
     কর্ণ
    0.45
    。
    0.45
     드릴
    0.44
     лю
    0.43
     symmetrically
    0.43
    POSITIVE LOGITS
     краё
    0.51
    協會
    0.50
    專輯
    0.47
    assoc
    0.46
    _{\
    0.45
     सरकारों
    0.45
    _',
    0.43
     खेती
    0.42
     مؤرشف
    0.42
     কর্তৃপক্ষের
    0.42
    Activations Density 0.000%

    No Known Activations