© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 409
    Prev
    Next
    INDEX
    Explanations

    urls, code, quotes, special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    0.79
     light
    0.72
     routine
    0.71
     probability
    0.70
     tra
    0.69
     log
    0.68
     mand
    0.68
     steering
    0.64
     vt
    0.64
     j
    0.64
    POSITIVE LOGITS
    Ин
    0.93
    РА
    0.90
    Ба
    0.89
    Ми
    0.87
    Ра
    0.82
    На
    0.82
     Ин
    0.81
    НЕ
    0.78
    Се
    0.78
     பயணம்
    0.78
    Activations Density 0.398%

    No Known Activations