© 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. 196293
    Prev
    Next
    INDEX
    Explanations

    wedding dress, breast milk, was elected

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

    intervening causes and sequential steps

    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
     নাকের
    0.52
     કરોડ
    0.51
     વિકાસ
    0.50
     వరకు
    0.49
    贰
    0.48
     विपक्षी
    0.48
    镜
    0.48
    缺陷
    0.48
     दुःख
    0.48
    腑
    0.47
    POSITIVE LOGITS
    t
    0.48
    சன்
    0.47
    явля
    0.46
     laboral
    0.46
    FEM
    0.45
    Prior
    0.44
     перено
    0.44
    はじ
    0.44
    CT
    0.43
    datei
    0.43
    Activations Density 0.000%

    No Known Activations