© 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. 22-GEMMASCOPE-2-RES-65K
    7. 7752
    Prev
    Next
    INDEX
    Explanations

    specific keywords followed by descriptors

    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_22_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
    தம்ப
    0.91
    ness
    0.86
    ounces
    0.85
    ism
    0.82
    ulates
    0.81
    tail
    0.80
    斕
    0.78
    ères
    0.77
    aries
    0.77
    ment
    0.76
    POSITIVE LOGITS
     වශ
    0.87
    വുമായ
    0.83
     условии
    0.82
     गरी
    0.81
     Sts
    0.79
     Uh
    0.78
     Sv
    0.77
     Depends
    0.77
     __________
    0.76
    種類の
    0.75
    Activations Density 0.220%

    No Known Activations