© 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
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 5296
    Prev
    Next
    INDEX
    Explanations

    list items start with punctuation, numbers, or specific words

    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
     көп
    0.58
     nejen
    0.57
    ewarm
    0.56
    iędzy
    0.54
    ண்கள்
    0.53
     основные
    0.52
     انصاف
    0.52
    °,
    0.51
    ishops
    0.51
     अधिकतम
    0.50
    POSITIVE LOGITS
     identifier
    0.70
     name
    0.70
    名为
    0.69
     bernama
    0.67
    name
    0.63
    を指定
    0.63
     varchar
    0.62
    Identifier
    0.61
     dicho
    0.61
     specifies
    0.61
    Activations Density 0.003%

    No Known Activations