© 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. 3355
    Prev
    Next
    INDEX
    Explanations

    build process

    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
    ב
    2.09
    к
    1.95
    ように
    1.95
    ー
    1.94
    서
    1.91
    о
    1.78
    亠
    1.72
    υ
    1.68
    сть
    1.67
    fficient
    1.59
    POSITIVE LOGITS
     quente
    1.65
    ية
    1.64
    िल
    1.61
    ারের
    1.61
    𝗙
    1.58
    nosed
    1.55
    ির
    1.54
    ن
    1.49
    𝗘
    1.49
    ます
    1.48
    Activations Density 0.022%

    No Known Activations