© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8072
    Prev
    Next
    INDEX
    Explanations

    focus on

    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_31_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
     compliqué
    0.90
    t
    0.86
    tain
    0.85
     véritable
    0.84
     énorm
    0.82
    uene
    0.81
    Hasta
    0.79
    oblig
    0.78
    necess
    0.77
    vamos
    0.77
    POSITIVE LOGITS
     электрон
    0.81
     esophageal
    0.69
     блю
    0.68
    цию
    0.67
    (.*
    0.66
     keren
    0.64
    дный
    0.64
     dolayı
    0.63
     умолчанию
    0.62
     cardiomyocyte
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.