© 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. 132469
    Prev
    Next
    INDEX
    Explanations

    noun phrases and their contexts

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

    when it is appropriate

    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
    牫
    0.42
    IsEmpty
    0.40
    exports
    0.39
    qt
    0.39
     smells
    0.39
     بع
    0.39
     مذا
    0.39
     المنتج
    0.39
    您
    0.38
    قر
    0.38
    POSITIVE LOGITS
     шири
    0.51
     расши
    0.43
     சரி
    0.43
    y
    0.43
     subdue
    0.43
    eiro
    0.43
    ,-
    0.42
    %-
    0.42
     իր
    0.42
     ditambah
    0.42
    Activations Density 0.000%

    No Known Activations