© 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. 2509
    Prev
    Next
    INDEX
    Explanations

    refuse to

    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
    ul
    1.84
    燹
    1.72
    ieu
    1.64
     behö
    1.63
    arxiv
    1.61
    warm
    1.60
     is
    1.59
    ES
    1.54
    G
    1.54
     plaus
    1.52
    POSITIVE LOGITS
    ي
    2.89
    י
    2.52
    ি
    2.23
    й
    2.23
    y
    2.16
    ל
    2.14
    ক্স
    2.13
    ન
    2.09
    ف
    2.08
    פ
    2.08
    Activations Density 0.002%

    No Known Activations