© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6066
    Prev
    Next
    INDEX
    Explanations

    extracting specific information or metadata

    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
     their
    0.84
     Their
    0.74
    在
    0.71
    他们的
    0.71
     laps
    0.69
     During
    0.66
    返回值
    0.66
    \
    0.65
    ↵↵
    0.65
     crowding
    0.65
    POSITIVE LOGITS
     amelyek
    1.16
     данных
    1.09
    Semantic
    1.08
     gegevens
    1.08
     données
    1.04
    データ
    1.03
     fondée
    1.02
     Datenbank
    1.01
    Информация
    1.00
     fichiers
    0.99
    Activations Density 1.641%

    No Known Activations