© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 37620
    Prev
    Next
    INDEX
    Explanations

    fasteners, mechanical components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     وعلى
    2.30
    丆
    2.02
    ر
    1.99
     dàng
    1.98
    ু
    1.91
     helst
    1.91
    য়
    1.81
    ပ်
    1.80
     bandeja
    1.80
     ODBC
    1.80
    POSITIVE LOGITS
    ৫
    2.42
    ı
    2.25
    ৮
    2.19
    на
    2.13
    ९
    2.11
    ৬
    1.98
    heastern
    1.98
    he
    1.94
    не
    1.88
    ру
    1.88
    Activations Density 0.003%

    No Known Activations