© 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. 2319
    Prev
    Next
    INDEX
    Explanations

    hatching and timing

    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
    cough
    1.39
     overturn
    1.38
    posts
    1.37
     Misalnya
    1.37
    गिर
    1.35
    &$\
    1.33
    pointe
    1.32
    یر
    1.32
     внимания
    1.31
    દિવસ
    1.30
    POSITIVE LOGITS
    y
    2.04
    ר
    1.79
    ل
    1.66
    じる
    1.52
    ёт
    1.45
    רת
    1.41
    财经
    1.35
    el
    1.33
    рати
    1.32
     eerst
    1.32
    Activations Density 0.005%

    No Known Activations