© 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. 1683
    Prev
    Next
    INDEX
    Explanations

    code else branches

    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
    ة
    2.08
     Т
    1.98
     Knowing
    1.89
    ва
    1.87
     TextStyle
    1.77
    esses
    1.70
    ɱ
    1.69
    рои
    1.65
     поэтому
    1.64
    ‬‬
    1.63
    POSITIVE LOGITS
     else
    2.29
     nghiệp
    1.83
    ر
    1.73
     combattre
    1.70
    ó
    1.66
    jenis
    1.64
     egen
    1.64
    ই
    1.63
     endroits
    1.63
    is
    1.63
    Activations Density 0.054%

    No Known Activations