© 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. 5300
    Prev
    Next
    INDEX
    Explanations

    currency and mass units

    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
    ן
    1.62
    uğu
    1.45
    ας
    1.45
    ్‌
    1.41
    thebetter
    1.41
     постепен
    1.38
    ר
    1.37
     средства
    1.36
     tutur
    1.36
    HandleTypeDef
    1.35
    POSITIVE LOGITS
    بي
    1.72
    很
    1.66
    '
    1.58
    И
    1.55
    men
    1.54
    ت
    1.54
    man
    1.48
    itionen
    1.45
    leistung
    1.45
    nummer
    1.44
    Activations Density 0.214%

    No Known Activations