© 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. 43341
    Prev
    Next
    INDEX
    Explanations

    prior to or associated with

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

    dew-kissed descriptions

    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
    ！！！
    0.45
    ुट
    0.42
    ？
    0.41
    ！”
    0.40
     crores
    0.40
    ”。
    0.40
    】
    0.40
    ेंड
    0.39
    ۔
    0.38
     ALWAYS
    0.38
    POSITIVE LOGITS
     zusätz
    0.46
     dengan
    0.46
     avec
    0.43
     với
    0.42
    스와
    0.42
     Avec
    0.41
     modelli
    0.41
     новые
    0.41
     مدل
    0.41
     മറ്റു
    0.41
    Activations Density 0.001%

    No Known Activations