© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24548
    Prev
    Next
    INDEX
    Explanations

    community / space / patches / dance / zones

    np_acts-logits-general · gemini-2.5-flash-lite

    lists and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     podpor
    0.53
     கட்டுமான
    0.50
    __.
    0.49
    ufact
    0.48
     bottlene
    0.48
     polymer
    0.47
    మ్యాచ్
    0.47
     polymers
    0.47
     microsc
    0.46
     octahedral
    0.46
    POSITIVE LOGITS
    春天
    0.46
    陳
    0.45
    ขอ
    0.45
    伊
    0.44
    คล
    0.43
    全新
    0.43
    求
    0.43
    สุ
    0.42
    陈
    0.41
    悉
    0.41
    Activations Density 0.000%

    No Known Activations