© 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. 200238
    Prev
    Next
    INDEX
    Explanations

    decorated, firm, ritzy, magic, nightclubs, large

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

    locally or driving

    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
     Amsterdam
    0.47
    c
    0.46
     iff
    0.45
     due
    0.45
     zarówno
    0.45
     Arrays
    0.44
     Booking
    0.44
     claims
    0.43
     January
    0.43
     Travels
    0.43
    POSITIVE LOGITS
     километров
    0.52
     algoritmo
    0.48
     клини
    0.48
    terror
    0.47
    clinical
    0.46
    嚇
    0.46
     случайно
    0.46
     الأكثر
    0.46
    engineered
    0.45
    ложение
    0.45
    Activations Density 0.000%

    No Known Activations