© 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. 158991
    Prev
    Next
    INDEX
    Explanations

    steel and materials

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

    RNA molecules and industrial terms

    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
    ற
    0.46
     prolog
    0.46
     fij
    0.45
     ибо
    0.45
     фи
    0.45
     x
    0.45
    ưa
    0.44
     bn
    0.44
     gdyż
    0.44
     இந்ந
    0.43
    POSITIVE LOGITS
    <0xAD>
    0.46
     Edelstahl
    0.46
     acciaio
    0.45
    鎳
    0.44
    be
    0.42
     contoured
    0.42
     steel
    0.42
    當時
    0.41
    鋼
    0.41
     begann
    0.40
    Activations Density 0.001%

    No Known Activations