© 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-262K
    7. 11980
    Prev
    Next
    INDEX
    Explanations

    )"

    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_262k_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
     lieux
    1.37
    д
    1.33
    ри
    1.30
    sides
    1.29
    ی
    1.27
    ের
    1.26
    ‍♀️
    1.23
    sites
    1.23
    songs
    1.21
    leqslant
    1.20
    POSITIVE LOGITS
    ᐟ
    1.29
    el
    1.24
     быть
    1.17
    ங்கிணை
    1.17
     sā
    1.16
     قاعد
    1.16
    。.
    1.14
    ので
    1.14
    ండో
    1.10
    뷊
    1.09
    Activations Density 0.138%

    No Known Activations