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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 2687
    Prev
    Next
    INDEX
    Explanations

    is a, el, una, an, the

    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_24_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
    Start
    0.86
    ﻝ
    0.83
    Templ
    0.75
    Todo
    0.73
    Tra
    0.73
    รู
    0.73
    Dir
    0.71
    ;'
    0.71
    lld
    0.71
    Specify
    0.71
    POSITIVE LOGITS
     istilah
    0.96
     macam
    0.86
     difference
    0.83
     भाजी
    0.78
     perbedaan
    0.77
     meant
    0.75
    ಗಳಿಗೆ
    0.74
     differences
    0.73
    agnetic
    0.73
    doctrine
    0.73
    Activations Density 0.003%

    No Known Activations