© 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. 137983
    Prev
    Next
    INDEX
    Explanations

    bitter taste, compact products

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

    border town charm

    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
     काळ
    0.47
     seminal
    0.46
    ד
    0.46
     numerous
    0.45
    瑾
    0.44
     serve
    0.43
     வழ
    0.43
     जीके
    0.43
    дом
    0.43
     युग्
    0.43
    POSITIVE LOGITS
    ليات
    0.47
     दवाओं
    0.43
     biota
    0.42
     الزد
    0.41
    花
    0.40
    ኣ
    0.40
     Arias
    0.40
     Subsect
    0.39
    合并
    0.39
     ওষুধের
    0.39
    Activations Density 0.000%

    No Known Activations