© 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. 221929
    Prev
    Next
    INDEX
    Explanations

    paths to, state memory, speed up

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

    client / factors / inflated

    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
    構築
    0.44
    瘴
    0.44
    ેટ
    0.44
     इस्लाम
    0.44
    วาม
    0.44
    建て
    0.43
    毌
    0.43
    ជ
    0.43
    终
    0.42
    Theorem
    0.42
    POSITIVE LOGITS
     (?)
    0.48
    month
    0.47
    world
    0.47
     কেবল
    0.45
     selezion
    0.45
    ON
    0.44
    ORE
    0.43
     заяв
    0.43
     निर्दिष्ट
    0.43
     mailed
    0.42
    Activations Density 0.001%

    No Known Activations