© 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-16K
    7. 2458
    Prev
    Next
    INDEX
    Explanations

    I've

    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_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
     دارم
    0.93
     我的
    0.90
     my
    0.82
     puedo
    0.80
     我
    0.80
     моей
    0.80
     எனக்கு
    0.78
     meine
    0.76
     znajdu
    0.75
     forstå
    0.75
    POSITIVE LOGITS
    推荐
    0.77
     pasión
    0.76
    آپ
    0.76
     비해
    0.75
     apasion
    0.74
     추천
    0.74
     omitted
    0.73
    <0xAC>
    0.71
    criar
    0.71
     omitting
    0.70
    Activations Density 0.219%

    No Known Activations