© 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. 151378
    Prev
    Next
    INDEX
    Explanations

    annual periods

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

    master manipulator, each month, Critical Infrastructure, predict what, cycles, age

    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
     Master
    0.50
     Found
    0.48
    ॰
    0.44
    inie
    0.44
    aron
    0.43
     Landmark
    0.43
     Used
    0.43
    ارات
    0.43
     Trademark
    0.42
     Landmarks
    0.42
    POSITIVE LOGITS
    悶
    0.54
     ډول
    0.50
    ወ
    0.50
    而言
    0.49
    腑
    0.48
     то
    0.48
     ਗ
    0.48
     організа
    0.47
    Пі
    0.47
     Сі
    0.46
    Activations Density 0.001%

    No Known Activations