© 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. 2253
    Prev
    Next
    INDEX
    Explanations

    delve deeper into topics

    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
    te
    2.48
    emn
    1.95
    ре
    1.91
    ity
    1.87
     precincts
    1.83
    lar
    1.82
    с
    1.81
    е
    1.81
    ނ
    1.79
    его
    1.77
    POSITIVE LOGITS
    ας
    2.14
     lieber
    2.00
    ֨
    1.88
    勬
    1.88
     суда
    1.87
     persen
    1.85
     दूसरी
    1.84
    ໌
    1.83
    ᱝ
    1.81
     Puedes
    1.79
    Activations Density 0.080%

    No Known Activations