© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 12280
    Prev
    Next
    INDEX
    Explanations

    proactive risk

    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
    自治区
    2.11
    पी
    1.73
    彠
    1.62
    घव
    1.61
    器
    1.57
    铑
    1.56
    病例
    1.55
    𝘻
    1.55
    药品
    1.55
    犸
    1.55
    POSITIVE LOGITS
    '
    2.80
    ’
    2.03
    ag
    1.99
    ing
    1.91
    ses
    1.87
    .
    1.77
    со
    1.72
    1.70
    ak
    1.69
    ar
    1.68
    Activations Density 0.133%

    No Known Activations