© 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. 11153
    Prev
    Next
    INDEX
    Explanations

    key context

    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
    क
    3.23
    да
    3.08
    ن
    2.97
     DEX
    2.79
     excuses
    2.79
    ваний
    2.78
    ような
    2.77
    Pressed
    2.67
     sows
    2.66
     phúc
    2.61
    POSITIVE LOGITS
    ット
    2.72
     alleen
    2.70
    cloak
    2.56
    심히
    2.50
    ệt
    2.50
    ا
    2.48
    бір
    2.42
    िंग
    2.40
    બ
    2.39
    یه
    2.36
    Activations Density 0.122%

    No Known Activations