© 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-16K
    7. 1497
    Prev
    Next
    INDEX
    Explanations

    social media platforms

    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_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
    ة
    2.60
    ்ச்ச
    2.49
    هن
    2.46
    ing
    2.46
    ിയ
    2.28
    ी
    2.18
    ा
    2.16
    yog
    2.12
    |\
    2.12
    ும்
    2.08
    POSITIVE LOGITS
    ু
    2.92
    jší
    2.71
     peintre
    2.62
    cstdlib
    2.51
     sword
    2.40
    ان
    2.36
    сть
    2.34
    ুয়া
    2.31
    quiera
    2.29
    دی
    2.28
    Activations Density 0.275%

    No Known Activations