© 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. 2007
    Prev
    Next
    INDEX
    Explanations

    code execution flow

    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
    ت
    1.74
    een
    1.74
    黼
    1.65
    eine
    1.64
    ート
    1.62
    是通过
    1.50
    érieures
    1.49
    ेक
    1.48
    تهم
    1.47
    मारी
    1.46
    POSITIVE LOGITS
    orld
    1.69
    ١
    1.62
     kia
    1.60
     shove
    1.53
    Sqrt
    1.52
     укра
    1.50
     taget
    1.50
    v
    1.49
    of
    1.49
    ▶
    1.48
    Activations Density 0.236%

    No Known Activations