© 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. 31706
    Prev
    Next
    INDEX
    Explanations

    Proton Mail VPN headless HALving

    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
    ل
    1.80
    न
    1.77
    ن
    1.58
    ান
    1.55
    ある
    1.48
    ᴅ
    1.47
    يه
    1.45
     hibernate
    1.45
    𝒐
    1.45
    ский
    1.44
    POSITIVE LOGITS
    های
    2.14
    ς
    2.03
    х
    1.70
    af
    1.67
    니
    1.66
    cz
    1.64
    cs
    1.62
    ć
    1.61
    piece
    1.60
    ात
    1.58
    Activations Density 0.015%

    No Known Activations