© 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. 12-GEMMASCOPE-2-RES-262K
    4. 31917
    Prev
    Next
    INDEX
    Explanations

    genealogy or catalog

    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
    ра
    1.75
    :
    1.66
    ?
    1.62
     irão
    1.56
    ventions
    1.55
     expresa
    1.52
    ോട്ട്
    1.48
    clusion
    1.44
     обращения
    1.44
    す楽
    1.41
    POSITIVE LOGITS
    ле
    1.84
    د
    1.79
    ﺔ
    1.70
    라
    1.54
    ानुसार
    1.53
    皂
    1.52
    ev
    1.48
    ్‌
    1.48
    وغ
    1.46
    OL
    1.45
    Activations Density 0.005%

    No Known Activations