© 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. 111319
    Prev
    Next
    INDEX
    Explanations

    critical illness, available item, Korean tea

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

    automated driving systems

    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
     pede
    0.54
     năm
    0.50
    <0x80>
    0.48
    𝗇
    0.48
     webpages
    0.47
     globales
    0.46
    globals
    0.45
    ань
    0.45
    ုံ
    0.44
     akzept
    0.43
    POSITIVE LOGITS
    Buttons
    0.47
    Order
    0.43
    Saf
    0.43
    Serum
    0.43
    Borrow
    0.42
    0.42
    Raw
    0.42
    Module
    0.42
    㭐
    0.42
    Power
    0.41
    Activations Density 0.001%

    No Known Activations