© 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. 27749
    Prev
    Next
    INDEX
    Explanations

    these two

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

    Repositories, infants, VNF

    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
     patt
    0.48
    play
    0.47
    role
    0.47
    gif
    0.46
     ¨
    0.45
    je
    0.45
     misa
    0.44
    ley
    0.43
     rom
    0.43
    lien
    0.43
    POSITIVE LOGITS
    这两个
    0.63
    这两
    0.60
    ებზე
    0.49
    እንደ
    0.48
    ടുത്തു
    0.48
    เหล่านี้
    0.47
    يع
    0.47
    Neighbors
    0.47
    辄
    0.47
     هذه
    0.46
    Activations Density 0.000%

    No Known Activations