© 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. 243393
    Prev
    Next
    INDEX
    Explanations

    information about specific entities

    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
    庄
    0.50
    สัง
    0.40
    $[
    0.40
    ў
    0.40
     Natale
    0.40
    ീകരിച്ച
    0.38
    ะ
    0.38
    友
    0.37
    炲
    0.37
    гла
    0.37
    POSITIVE LOGITS
     raíz
    0.54
     Tecnología
    0.51
    öyle
    0.50
    ına
    0.50
     følge
    0.50
    ಟರ್
    0.49
     ######
    0.49
     टेक्स्ट
    0.49
     কাত
    0.48
    ineri
    0.48
    Activations Density 0.000%

    No Known Activations