© 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. 10802
    Prev
    Next
    INDEX
    Explanations

    player data, possibilities, code declarations

    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
    ែក
    1.58
    Ⲇ
    1.47
    ‌و
    1.46
    ीय
    1.45
    TypeDef
    1.39
    ٖ
    1.38
     distinguishers
    1.38
    Ἐ
    1.36
    িয়াম
    1.36
    ién
    1.35
    POSITIVE LOGITS
    िक
    1.88
    новый
    1.62
     giống
    1.57
    ালী
    1.52
     использоваться
    1.42
     lama
    1.41
     कहना
    1.39
     laurels
    1.39
    ่านั้น
    1.39
     реда
    1.39
    Activations Density 0.000%

    No Known Activations