© 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. 8284
    Prev
    Next
    INDEX
    Explanations

    words starting with ce

    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
    к
    0.94
     sano
    0.91
     resulta
    0.84
    ান্স
    0.83
     किरदार
    0.82
    싯
    0.81
    फॉर्मेशन
    0.81
    lim
    0.80
     snag
    0.79
    ә
    0.79
    POSITIVE LOGITS
    estial
    1.43
     div
    1.03
    usescu
    1.01
    ificates
    0.98
    ნობ
    0.98
    ANEOUS
    0.95
    elessly
    0.94
    estis
    0.94
    fires
    0.92
    eteries
    0.92
    Activations Density 0.097%

    No Known Activations