© 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. 31857
    Prev
    Next
    INDEX
    Explanations

    departure date and time

    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
    做
    2.05
    های
    1.84
    Те
    1.74
    ور
    1.68
     Thực
    1.66
    i
    1.66
    os
    1.65
    渽
    1.64
    dong
    1.63
     dịp
    1.60
    POSITIVE LOGITS
     비롯
    1.98
    ましたが
    1.78
    т
    1.76
    ள்ளார்
    1.75
    ள்ளனர்
    1.75
    이면
    1.71
    ндә
    1.70
    습니다
    1.69
    েই
    1.68
    শকা
    1.68
    Activations Density 0.003%

    No Known Activations