© 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. 10078
    Prev
    Next
    INDEX
    Explanations

    Adam and Genesis

    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
     annat
    3.36
    ل
    3.35
    ▫
    2.82
    ⌒
    2.66
    其中的
    2.65
    ली
    2.62
    ות
    2.57
     else
    2.54
     gosh
    2.44
    От
    2.43
    POSITIVE LOGITS
    ع
    3.97
    ян
    3.00
    ب
    2.90
    یز
    2.67
    ersion
    2.66
    ड
    2.62
    ising
    2.58
    شاه
    2.57
    во
    2.57
    なぜ
    2.56
    Activations Density 0.053%

    No Known Activations