© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3222
    Prev
    Next
    INDEX
    Explanations

    added to, beginning, licensing, short task, greater

    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_24_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
    橦
    0.88
     Seite
    0.77
     greedy
    0.73
     kube
    0.73
    ছন
    0.72
     cotton
    0.72
     shovel
    0.72
     capítulo
    0.71
     gripped
    0.71
     resto
    0.70
    POSITIVE LOGITS
    ન
    0.87
    And
    0.86
    Ook
    0.84
    Nau
    0.83
    Lionel
    0.81
    Uit
    0.80
    IL
    0.80
    ETT
    0.79
    Aging
    0.79
    X
    0.78
    Activations Density 0.000%

    No Known Activations