© 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. 7715
    Prev
    Next
    INDEX
    Explanations

    semiconductor device substrate filling

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

    multilingual text snippets

    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
    <unused451>
    0.31
    <unused1113>
    0.27
    ၆
    0.27
    <unused483>
    0.27
    𝟯
    0.26
    ⑸
    0.26
    <unused67>
    0.26
     없고
    0.26
    <unused512>
    0.26
    <unused1112>
    0.26
    POSITIVE LOGITS
     The
    0.26
    爫
    0.24
     ھ
    0.24
     pous
    0.24
     logiciel
    0.23
     た
    0.22
    חת
    0.22
    ﻋ
    0.22
     latter
    0.21
     ۋە
    0.21
    Activations Density 0.037%

    No Known Activations