© 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. 208211
    Prev
    Next
    INDEX
    Explanations

    categories and specific entities

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

    structural delimiters

    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
    ್ರಿ
    0.54
    у
    0.50
    युक्त
    0.46
    يين
    0.46
    騾
    0.46
    anz
    0.46
    د
    0.46
    ным
    0.46
    soluble
    0.45
    kut
    0.44
    POSITIVE LOGITS
     kategorii
    0.49
    :_
    0.47
     Kategorie
    0.45
    (_
    0.44
     joc
    0.44
     kategorie
    0.44
     Kop
    0.44
    แมนเชสเตอร์ซิตี
    0.43
     👇
    0.43
     maß
    0.43
    Activations Density 0.001%

    No Known Activations