© 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. 24
    Prev
    Next
    INDEX
    Explanations

    flagship phones, navy pencil, Independence

    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
    ati
    1.02
    .
    0.99
    *
    0.88
    ...
    0.77
    acao
    0.75
    (
    0.75
    "
    0.74
    ,
    0.72
    [
    0.71
    ला
    0.70
    POSITIVE LOGITS
    προ
    1.02
     प्रशंसकों
    0.93
    dtype
    0.93
     பல்வேறு
    0.92
    精致
    0.92
     autoestima
    0.92
    მასრულ
    0.91
     သ
    0.91
    ບໍລິ
    0.91
     conglomer
    0.90
    Activations Density 0.000%

    No Known Activations