© 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. 10390
    Prev
    Next
    INDEX
    Explanations

    ** and Go

    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
    dır
    2.34
    or
    2.25
     predicament
    2.09
     trove
    2.06
    ু
    2.04
     faire
    2.03
    al
    1.99
     Painlev
    1.97
    సీపీ
    1.96
     bezel
    1.95
    POSITIVE LOGITS
    pping
    2.06
    𝑳
    2.04
    훙
    1.98
    ╁
    1.97
    ਸ
    1.94
    rmann
    1.90
    ␮
    1.90
     MLE
    1.89
    𝙇
    1.87
    𝙧
    1.85
    Activations Density 0.657%

    No Known Activations