© 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. 124474
    Prev
    Next
    INDEX
    Explanations

    when time or events align

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

    Depreciation Stop, Ada Lovelace, CSR efforts

    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
    getLocal
    0.54
    챔
    0.49
     Св
    0.48
    수의
    0.47
    arak
    0.46
     Khi
    0.45
    ведения
    0.45
     ದೇವರ
    0.45
     sensed
    0.44
    т
    0.44
    POSITIVE LOGITS
     pric
    0.48
    ലീസ്
    0.46
    robespierre
    0.46
     outflow
    0.44
    プター
    0.44
    :&
    0.44
     neuromuscular
    0.44
     ejecutivo
    0.43
     ibuprofen
    0.43
    "-------
    0.43
    Activations Density 0.001%

    No Known Activations