© 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. 43421
    Prev
    Next
    INDEX
    Explanations

    latitude

    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
     вследствие
    1.62
    bearer
    1.52
     êtres
    1.48
    ساز
    1.45
    "-------
    1.43
    ivité
    1.42
    و
    1.38
    yse
    1.37
    pores
    1.34
    wagen
    1.32
    POSITIVE LOGITS
    ৭
    1.92
     stately
    1.74
    びに
    1.73
     видеть
    1.70
    ین
    1.57
     inconsider
    1.57
     grot
    1.56
    П
    1.56
    ﺮ
    1.56
    ᅴ
    1.55
    Activations Density 0.002%

    No Known Activations