© 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. 2438
    Prev
    Next
    INDEX
    Explanations

    default settings for browser, font, email

    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
    ا
    1.42
    ح
    1.29
    a
    1.14
     рассчита
    1.06
    こちらの
    1.01
    л
    1.01
    ில்
    1.01
    лля
    1.01
    er
    0.99
    最重要的
    0.98
    POSITIVE LOGITS
    Corollary
    1.51
     esteem
    1.47
     aves
    1.46
     cassava
    1.45
    isVisible
    1.43
     JCV
    1.42
    Commun
    1.39
     Corollary
    1.37
    埃及
    1.37
    ᴇ
    1.35
    Activations Density 0.003%

    No Known Activations