© 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. 74625
    Prev
    Next
    INDEX
    Explanations

    medical and herbal remedies

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

    selection or choice

    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
     berbagai
    0.45
     Sneakers
    0.43
     çeşitli
    0.43
     tbh
    0.41
     yanında
    0.41
     nhiều
    0.40
     paylaş
    0.40
    ~(\
    0.39
     seksual
    0.39
    querySelectorAll
    0.39
    POSITIVE LOGITS
     faraway
    0.48
    이면
    0.48
     whichever
    0.44
    анта
    0.44
    Selecion
    0.44
    selecting
    0.42
    virgin
    0.42
     if
    0.42
     chois
    0.41
     ถ้า
    0.41
    Activations Density 0.005%

    No Known Activations