© 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. 198215
    Prev
    Next
    INDEX
    Explanations

    the terms return plant trademarks magnitude

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

    tied to productivity or worth

    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
     것이
    0.48
    戰爭
    0.46
     pewno
    0.45
    야
    0.45
     갔
    0.45
    atás
    0.44
     cycle
    0.44
     करती
    0.44
     transporter
    0.43
     CYCLE
    0.43
    POSITIVE LOGITS
    ('/')
    0.50
    धित
    0.48
    လျှ
    0.47
     profonde
    0.46
    個セット
    0.46
    σεις
    0.45
     Dawkins
    0.44
    ಠ
    0.43
    佻
    0.43
    lichess
    0.43
    Activations Density 0.001%

    No Known Activations