© 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-262K
    7. 11927
    Prev
    Next
    INDEX
    Explanations

    destruction function

    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
    𝐤
    3.38
    𝐳
    3.30
    𝐦
    3.24
    𝐫
    3.06
    場合
    3.01
    দের
    2.99
    𝐧
    2.98
    ^{*}
    2.95
    ^{*},
    2.94
    ‍♂️
    2.84
    POSITIVE LOGITS
    бин
    3.28
     связано
    3.11
    ти
    2.97
    ى
    2.94
    тический
    2.85
    ী
    2.84
    ्या
    2.82
    spaper
    2.81
    in
    2.80
    словия
    2.77
    Activations Density 0.019%

    No Known Activations