© 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. 380
    Prev
    Next
    INDEX
    Explanations

    approving, agreed, category, packs

    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
     불구하고
    1.02
    かつ
    0.97
    ACIÓN
    0.96
     Qxb
    0.95
    쐞
    0.95
     Его
    0.95
    ificacion
    0.94
    阝
    0.94
    AssetsResponse
    0.94
     teilweise
    0.93
    POSITIVE LOGITS
    ad
    0.97
    am
    0.94
    diy
    0.93
    ders
    0.89
    この
    0.88
    تی
    0.84
     customizations
    0.82
     democratization
    0.80
    dif
    0.77
    c
    0.77
    Activations Density 0.000%

    No Known Activations