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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8520
    Prev
    Next
    INDEX
    Explanations

    "你" followed by future/action words

    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_16k_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
    ل
    2.36
    ่
    1.95
    č
    1.93
    на
    1.88
    لوں
    1.76
    ко
    1.70
    новых
    1.70
    үүн
    1.69
    り
    1.69
     }));
    1.64
    POSITIVE LOGITS
    ۰۰
    1.45
    ssss
    1.42
    THING
    1.41
    su
    1.38
    mma
    1.38
    adı
    1.35
    eer
    1.34
     overwritten
    1.34
    ‌است
    1.31
    hift
    1.30
    Activations Density 0.033%

    No Known Activations