© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9777
    Prev
    Next
    INDEX
    Explanations

    hats

    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_262k_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
    η
    2.87
    ták
    2.67
    Tapi
    2.64
    可以说
    2.59
    यची
    2.58
     behar
    2.51
    य
    2.50
    maßen
    2.47
    ও
    2.47
    ется
    2.42
    POSITIVE LOGITS
    การ
    3.07
     gxh
    2.95
    ле
    2.94
    ,-\
    2.87
     disapp
    2.84
     greed
    2.81
     accueill
    2.80
     waahanga
    2.80
     ITEMIZED
    2.76
    ">${
    2.72
    Activations Density 0.019%

    No Known Activations