© 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. 120919
    Prev
    Next
    INDEX
    Explanations

    years or historical periods

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

    years and dates

    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
    轺
    0.47
     kuning
    0.46
     papp
    0.46
     ढक
    0.46
     सर्वप्रथम
    0.45
    ribut
    0.45
     pierwszym
    0.44
     ២
    0.43
     ढ
    0.43
     latest
    0.43
    POSITIVE LOGITS
    .
    0.55
    %
    0.49
    Brexit
    0.45
    ティ
    0.44
    Nx
    0.43
    ЭС
    0.43
    тов
    0.42
    ρές
    0.42
    жие
    0.42
    いた
    0.41
    Activations Density 0.023%

    No Known Activations