© 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. 168421
    Prev
    Next
    INDEX
    Explanations

    leftover spice mix

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

    regulation and risk

    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
    懈
    0.46
     coisas
    0.45
    Tropical
    0.44
     Kiara
    0.40
     سارے
    0.40
     gimm
    0.40
     tenere
    0.40
     carina
    0.39
     cosas
    0.39
     ausge
    0.39
    POSITIVE LOGITS
     पुरात
    0.50
    ę
    0.48
    ingle
    0.47
    ?
    0.47
     поколения
    0.47
     Launcher
    0.47
    ມັນ
    0.46
    iss
    0.46
     ஆண்டுகளாக
    0.45
    ys
    0.44
    Activations Density 0.000%

    No Known Activations