© 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. 13
    Prev
    Next
    INDEX
    Explanations

    violence and abuse

    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
    ر
    1.07
    か
    0.99
    د
    0.97
    ع
    0.96
    ik
    0.94
    з
    0.92
    其他
    0.89
    er
    0.85
    с
    0.85
    el
    0.81
    POSITIVE LOGITS
     whatnot
    1.13
    romeda
    0.78
    radiative
    0.75
     Subsidi
    0.72
     nanofibers
    0.71
     biofilms
    0.70
     inextricably
    0.66
     goddesses
    0.65
     figuratively
    0.65
     blockchains
    0.64
    Activations Density 1.989%

    No Known Activations