© 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-262K
    7. 9859
    Prev
    Next
    INDEX
    Explanations

    Do you want me to explain

    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_262k_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
    HING
    1.78
    𝗟
    1.67
     viên
    1.62
    𝗠
    1.50
    ленні
    1.49
     virtue
    1.48
    ibirsk
    1.46
    िक
    1.46
     sou
    1.45
    istra
    1.44
    POSITIVE LOGITS
    a
    2.01
    o
    1.82
    u
    1.62
    ة
    1.57
    e
    1.55
    an
    1.52
    了
    1.51
    ம்
    1.50
    Inline
    1.43
    ał
    1.43
    Activations Density 0.033%

    No Known Activations