© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 654
    Prev
    Next
    INDEX
    Explanations

    Okay

    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
    ް
    1.52
    ъ
    1.39
    ocyt
    1.38
    влека
    1.36
    ogne
    1.32
    jegyz
    1.30
    ि
    1.27
     notch
    1.27
    üche
    1.25
     systolic
    1.25
    POSITIVE LOGITS
    ן
    2.08
    jší
    1.79
    ه
    1.70
    দের
    1.67
    ו
    1.57
    رر
    1.52
    ান্স
    1.49
    انہ
    1.44
    give
    1.41
    다면
    1.38
    Activations Density 0.444%

    No Known Activations