© 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. 224598
    Prev
    Next
    INDEX
    Explanations

    places Delta Floor Blank

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

    medical symptoms and 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
    ли
    0.52
    சூ
    0.50
    ја
    0.49
     আমিও
    0.48
    ம்
    0.47
    ΙΑ
    0.47
    敝
    0.46
    Begin
    0.46
    Indust
    0.46
    ຈ
    0.46
    POSITIVE LOGITS
     związane
    0.48
     audiovis
    0.44
     wykony
    0.43
     Portrait
    0.43
    োপাধ
    0.41
     uden
    0.41
     Yel
    0.41
     yönet
    0.41
     Servlet
    0.41
     виконав
    0.41
    Activations Density 0.001%

    No Known Activations