© 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. 156716
    Prev
    Next
    INDEX
    Explanations

    private advertising

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

    financial consolidation

    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
     主要
    0.51
     culmination
    0.47
    utsu
    0.45
    ឬ
    0.45
     お知らせ
    0.45
     বেশ
    0.45
     सुरक्षा
    0.45
     mostly
    0.44
    enegro
    0.44
     shag
    0.44
    POSITIVE LOGITS
    ت
    0.60
    م
    0.53
     Databases
    0.52
    ج
    0.51
    لم
    0.51
    м
    0.51
    ك
    0.51
    лимпи
    0.50
    Assemble
    0.50
    ذلك
    0.49
    Activations Density 0.001%

    No Known Activations