© 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. 192161
    Prev
    Next
    INDEX
    Explanations

    "continue to be classified"

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

    categories and contexts

    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
    ографи
    0.44
     হেফাজ
    0.44
     약간
    0.44
     petri
    0.44
    )=\
    0.43
     aDict
    0.43
     scrape
    0.42
     rectangles
    0.42
    xx
    0.42
    ೋಜನ
    0.42
    POSITIVE LOGITS
     Führung
    0.54
     Noise
    0.50
     परामर्श
    0.48
    이었
    0.48
    itization
    0.46
     ۳
    0.46
     RISE
    0.45
     आवेग
    0.44
     Chick
    0.44
     FA
    0.44
    Activations Density 0.001%

    No Known Activations