© 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. 2196
    Prev
    Next
    INDEX
    Explanations

    audience questions

    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
    々に
    1.32
    ँ
    1.32
     oon
    1.31
    ασ
    1.30
    々の
    1.28
    মান
    1.28
    צא
    1.28
    alan
    1.25
    ou
    1.24
    ভিতে
    1.17
    POSITIVE LOGITS
    ق
    1.87
    ت
    1.67
    ير
    1.55
    و
    1.50
    ي
    1.49
    ه
    1.43
    ن
    1.43
    iados
    1.42
    ة
    1.39
    لا
    1.36
    Activations Density 0.060%

    No Known Activations