© 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. 47531
    Prev
    Next
    INDEX
    Explanations

    years and periods

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

    configuring services and facilities

    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
     кантора
    0.49
     dodging
    0.48
    どんどん
    0.46
     ಹೋಗ
    0.46
    幇
    0.45
    ให้น
    0.45
    会い
    0.45
    <unused88>
    0.45
    閲覧
    0.45
    годні
    0.45
    POSITIVE LOGITS
     perioada
    0.50
     licha
    0.49
    ♑
    0.47
     Jahre
    0.46
     své
    0.46
     as
    0.46
     años
    0.45
    ك
    0.44
    یت
    0.44
    years
    0.44
    Activations Density 0.001%

    No Known Activations