© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1417
    Prev
    Next
    INDEX
    Explanations

    body and physical aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glance
    3.03
    ,]
    3.02
    которые
    2.92
    ப்படி
    2.57
     Vgl
    2.56
    THING
    2.55
    णे
    2.54
    Nowadays
    2.54
    érie
    2.53
    ductory
    2.53
    POSITIVE LOGITS
     stature
    3.18
     entero
    3.00
    то
    2.89
    ب
    2.79
    om
    2.67
    нің
    2.67
    ق
    2.62
    ק
    2.61
    การ
    2.60
    de
    2.60
    Activations Density 0.314%

    No Known Activations