© 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. 225040
    Prev
    Next
    INDEX
    Explanations

    numbers and codes like Z3

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

    events, times, places, or conditions

    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
    ！！！！
    0.48
    ！！！
    0.47
     vyroben
    0.47
    Imports
    0.46
     निचे
    0.46
     তোলেন
    0.46
     Aussi
    0.46
     問
    0.46
     이는
    0.45
    ⓶
    0.44
    POSITIVE LOGITS
     रिजर्व
    0.46
    R
    0.46
    ea
    0.46
    system
    0.45
     indicador
    0.45
     ff
    0.44
     finde
    0.43
    s
    0.43
    ó
    0.43
     indicators
    0.42
    Activations Density 0.001%

    No Known Activations