© 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. 197391
    Prev
    Next
    INDEX
    Explanations

    non-English text

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

    accurately distinguish

    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
     süreç
    0.48
     Pairs
    0.47
     Competitive
    0.46
     compétition
    0.44
     WLAN
    0.44
    ूटूथ
    0.43
    ?
    0.43
     Rome
    0.43
     They
    0.42
     sfida
    0.42
    POSITIVE LOGITS
    이라고
    0.46
     मार
    0.46
    ﹊
    0.45
    న్నీ
    0.44
    ன்
    0.43
    リティ
    0.43
     ദേ
    0.43
    悛
    0.43
    クシー
    0.43
    侔
    0.43
    Activations Density 0.001%

    No Known Activations