© 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. 7656
    Prev
    Next
    INDEX
    Explanations

    socket, pack, glove

    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
    ли
    1.14
    ئة
    1.02
    可以
    0.99
    یں
    0.98
    ні
    0.97
    陬
    0.97
    ský
    0.95
     ત્યાં
    0.95
    ็ต
    0.91
    yeh
    0.89
    POSITIVE LOGITS
    د
    1.51
    OD
    1.47
    ES
    1.30
     viven
    1.27
    ET
    1.27
    ED
    1.27
    LE
    1.18
    MENTS
    1.18
     muut
    1.18
    FR
    1.16
    Activations Density 0.264%

    No Known Activations