© 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. 210666
    Prev
    Next
    INDEX
    Explanations

    arbitrator, proceedings, innovation

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

    also trying sequences

    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
    ing
    0.52
    manes
    0.49
    Sach
    0.48
    Metadata
    0.47
     (
    0.47
    erial
    0.46
    Ao
    0.44
    Hawk
    0.44
    a
    0.44
    al
    0.44
    POSITIVE LOGITS
    akkhati
    0.51
     серию
    0.48
    દર્
    0.48
     ссылку
    0.46
     millet
    0.46
     conglomerates
    0.46
     brus
    0.46
     desserts
    0.46
    ccgi
    0.45
    סים
    0.45
    Activations Density 0.001%

    No Known Activations