© 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. 1614
    Prev
    Next
    INDEX
    Explanations

    under price or conditions

    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
    ت
    7.32
    تهم
    5.05
    er
    4.97
    ন
    4.64
    이
    4.60
    ر
    4.49
    erne
    4.44
    ти
    4.34
    र
    4.34
    нды
    4.29
    POSITIVE LOGITS
    сти
    3.86
    सी
    3.49
    ../../
    3.35
    දී
    3.30
    ১
    3.19
    ly
    3.16
    neath
    3.15
    늦
    3.13
    ский
    3.05
    𝖚
    2.91
    Activations Density 1.393%

    No Known Activations