© 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. 1834
    Prev
    Next
    INDEX
    Explanations

    clear and clearer transitions

    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
    tion
    5.03
    ের
    4.88
    tu
    4.69
    s
    4.49
    ે
    4.42
    tive
    4.21
    ti
    4.12
    ात
    4.05
    t
    3.93
    tak
    3.91
    POSITIVE LOGITS
    ので
    4.11
    р
    4.06
    ف
    3.81
    و
    3.31
    его
    3.24
    д
    3.22
    ously
    3.12
    м
    3.04
    同比增长
    3.03
    ज
    2.95
    Activations Density 1.128%

    No Known Activations