© 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. 7728
    Prev
    Next
    INDEX
    Explanations

    code formatting and plot labels

    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
    ológ
    1.73
    née
    1.66
     Çocuk
    1.66
    ώνει
    1.63
     stata
    1.59
     özel
    1.58
     një
    1.55
    ą
    1.54
    ć
    1.52
    kül
    1.52
    POSITIVE LOGITS
    ك
    1.80
    ма
    1.59
    ynchron
    1.49
    ного
    1.43
     refuted
    1.42
    他不
    1.40
     reigned
    1.37
    ,
    1.34
    ти
    1.29
    েই
    1.29
    Activations Density 0.001%

    No Known Activations