© 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. 205
    Prev
    Next
    INDEX
    Explanations

    Okay, followed by comma

    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
    ни
    0.93
    м
    0.89
     прогнозы
    0.88
     થાય
    0.84
     وير
    0.82
    胛
    0.81
    го
    0.79
     việc
    0.79
    WIDTH
    0.79
    вели
    0.77
    POSITIVE LOGITS
    臾
    0.82
    ئے
    0.79
    nej
    0.76
    lijk
    0.76
    cn
    0.73
    kaz
    0.69
    ئیں
    0.67
    یک
    0.67
     अमल
    0.67
    buch
    0.66
    Activations Density 2.683%

    No Known Activations