© 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. 115538
    Prev
    Next
    INDEX
    Explanations

    hotel, espresso, route, specialist, interaction

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

    awkwardness, models, Yanderes, Broker, Bun

    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
    ى
    0.55
     source
    0.50
    having
    0.49
    نى
    0.48
     having
    0.47
    ct
    0.46
     it
    0.46
    amers
    0.46
    ن
    0.46
    you
    0.45
    POSITIVE LOGITS
     маршру
    0.52
     подробно
    0.51
     Zapata
    0.50
     બંને
    0.49
     серви
    0.46
     ત્રણ
    0.46
     взаимодействия
    0.46
     Jordi
    0.46
     диагностики
    0.46
     серии
    0.45
    Activations Density 0.001%

    No Known Activations