© 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. 174250
    Prev
    Next
    INDEX
    Explanations

    static and Italy

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

    early signs and discoveries

    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
    考核
    0.44
     продукти
    0.44
     ক্ষেপ
    0.44
     Konto
    0.43
    వ్ర
    0.43
     konsumen
    0.43
    杮
    0.43
     evalu
    0.43
    avaliacao
    0.43
     평가
    0.42
    POSITIVE LOGITS
     italy
    0.51
    ڈ
    0.42
    |-\
    0.41
     static
    0.41
    STATIC
    0.40
    یاء
    0.40
     UNIV
    0.40
    творе
    0.39
     UNNEEDED
    0.39
     mutl
    0.39
    Activations Density 0.001%

    No Known Activations