© 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. 175788
    Prev
    Next
    INDEX
    Explanations

    measurements of size

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

    what it's like

    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
    moto
    0.49
     آن‌ها
    0.49
    stab
    0.47
    1
    0.47
    ikk
    0.46
    total
    0.45
    áció
    0.44
     తా
    0.43
    random
    0.42
    持续
    0.42
    POSITIVE LOGITS
     unusually
    0.50
     millimeters
    0.45
     important
    0.44
     woolen
    0.44
     handkerchief
    0.43
     milliliters
    0.43
     centimeters
    0.43
    ޞ
    0.43
     मिलीमीटर
    0.42
     millions
    0.42
    Activations Density 0.001%

    No Known Activations