© 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. 10523
    Prev
    Next
    INDEX
    Explanations

    couple of

    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
    ী
    5.08
    ோ
    4.00
    ट
    3.92
    ש
    3.65
    べき
    3.35
    us
    3.34
    ्या
    3.29
    quela
    3.20
    ಾ
    3.18
    ారు
    3.15
    POSITIVE LOGITS
    ی
    4.76
    e
    4.29
    yyyyyyyy
    4.04
    eur
    4.03
    oğlu
    3.95
    ्स
    3.89
    enje
    3.81
    i
    3.77
    ggio
    3.72
    o
    3.71
    Activations Density 0.115%

    No Known Activations