© 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. 68904
    Prev
    Next
    INDEX
    Explanations

    Vehicle repair manual

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

    receiving

    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
     znajdu
    0.51
     উপকরণ
    0.49
     κατά
    0.48
     კან
    0.48
     কৃষ্ণ
    0.47
    (´
    0.46
     ত্রিশ
    0.45
     roky
    0.45
     beserta
    0.45
     protéines
    0.45
    POSITIVE LOGITS
    с
    0.49
    غ
    0.40
    конец
    0.39
    يا
    0.39
    ුව
    0.39
    كيد
    0.39
     arctic
    0.38
    riding
    0.38
     جسے
    0.38
    envs
    0.38
    Activations Density 0.001%

    No Known Activations