© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 527
    Prev
    Next
    INDEX
    Explanations

    severe medical consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    및
    0.81
    ન
    0.75
    ga
    0.74
    OL
    0.73
    me
    0.73
    mon
    0.73
    ্ড
    0.72
    ش
    0.71
    께
    0.71
    ف
    0.70
    POSITIVE LOGITS
    ar
    0.84
    ام
    0.84
    ot
    0.82
     empê
    0.81
    ק
    0.79
    ির
    0.75
    و
    0.74
    াই
    0.72
    ோ
    0.72
    на
    0.71
    Activations Density 0.807%

    No Known Activations