© 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. 179812
    Prev
    Next
    INDEX
    Explanations

    temporal markers and actions

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

    phrases starting with how

    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
    غير
    0.57
    ੋਂ
    0.54
    ز
    0.47
    freq
    0.45
    털
    0.45
    ielder
    0.45
    ోంది
    0.45
    خان
    0.44
    فون
    0.44
    ف
    0.44
    POSITIVE LOGITS
     vitth
    0.54
     专业
    0.54
     comprehensively
    0.47
    মিক্যাল
    0.46
     istit
    0.46
    ণিক
    0.46
     alkal
    0.44
     Postgraduate
    0.44
    ะนั้น
    0.44
     परामर्श
    0.44
    Activations Density 0.000%

    No Known Activations