© 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. 2451
    Prev
    Next
    INDEX
    Explanations

    json describing actions and plastic waste

    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
    ה
    4.20
    sylvania
    3.88
    a
    3.62
    tı
    3.43
    syair
    3.43
    ر
    3.37
    ется
    3.34
    ????????
    3.24
    ς
    3.23
    र
    3.22
    POSITIVE LOGITS
    و
    4.89
     불구하고
    4.62
    ك
    3.89
    िया
    3.32
    𝒂
    3.29
    ک
    3.22
    𝒕
    3.19
    𝒇
    2.99
    𝑺
    2.96
    ia
    2.93
    Activations Density 0.365%

    No Known Activations