© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 251198
    Prev
    Next
    INDEX
    Explanations

    commissaries and their activities

    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
    𠄌
    0.48
    看起来
    0.47
    ័យ
    0.46
     attempted
    0.46
    ੱਚ
    0.46
     হোমিওপ্যাথ
    0.45
    ぁ
    0.45
    Entering
    0.44
     наблюдения
    0.44
     উপস্থাপন
    0.43
    POSITIVE LOGITS
     commiss
    0.55
     Commiss
    0.51
    h
    0.51
     diamante
    0.49
     त्र
    0.49
    தில்
    0.47
     spar
    0.46
     cess
    0.46
     caff
    0.46
     muff
    0.45
    Activations Density 0.001%

    No Known Activations