© 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. 45476
    Prev
    Next
    INDEX
    Explanations

    different, end, interesting, Engineer, waiting, only

    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
    c
    2.36
    cale
    1.73
    a
    1.71
    i
    1.69
    on
    1.63
    ী
    1.55
    iens
    1.52
    ز
    1.52
    高兴
    1.45
     accad
    1.45
    POSITIVE LOGITS
    ্যালেঞ্জ
    1.95
    ാൻഡ്
    1.57
    masks
    1.56
    filenames
    1.47
    ంచి
    1.42
    시켜
    1.42
     وعند
    1.41
    ैनल
    1.40
    вый
    1.38
    patterns
    1.38
    Activations Density 0.000%

    No Known Activations