© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10393
    Prev
    Next
    INDEX
    Explanations

    function creating service instances

    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
    ן
    0.80
    ode
    0.74
    atch
    0.68
     प्रेग्नेंसी
    0.68
     qualche
    0.67
    icking
    0.66
    IN
    0.65
    oro
    0.65
    버
    0.65
    ches
    0.64
    POSITIVE LOGITS
    žila
    0.88
     kolon
    0.84
     vzduchu
    0.83
    aphosa
    0.82
    元的
    0.81
    zuat
    0.80
     udara
    0.80
     kapal
    0.80
     soát
    0.79
     skú
    0.79
    Activations Density 0.000%

    No Known Activations