© 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. 29-GEMMASCOPE-2-RES-65K
    7. 4252
    Prev
    Next
    INDEX
    Explanations

    font family: Open Sans

    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_29_width_65k_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
     SOAP
    0.65
    console
    0.65
    陡
    0.64
     console
    0.62
     sdf
    0.62
    窗
    0.61
    CPU
    0.60
     East
    0.59
     CPU
    0.58
     earnings
    0.57
    POSITIVE LOGITS
    inter
    0.78
     martyrs
    0.66
    Inter
    0.64
    ۋ
    0.62
    oMatrix
    0.62
    iono
    0.61
     जाहिर
    0.60
    wijk
    0.60
    리의
    0.60
    otives
    0.60
    Activations Density 0.148%

    No Known Activations