© 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. 204569
    Prev
    Next
    INDEX
    Explanations

    collaboration with, benefit from

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

    medical and social 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
     школовања
    0.52
     определя
    0.47
     চাওয়া
    0.47
     చేశ
    0.46
     терро
    0.44
    參数
    0.44
    秇
    0.44
     soát
    0.43
    гляда
    0.43
    婹
    0.43
    POSITIVE LOGITS
     नाट्य
    0.47
    毛
    0.46
    ຖື
    0.45
     berikut
    0.45
    umo
    0.44
    णाल
    0.44
     develops
    0.43
     provoqu
    0.43
    ドウ
    0.42
    ුරු
    0.42
    Activations Density 0.000%

    No Known Activations