© 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. 312
    Prev
    Next
    INDEX
    Explanations

    local, require, for, FOR

    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
     тек
    0.82
    Birth
    0.80
    Stre
    0.79
    ak
    0.78
     explicando
    0.78
    ibald
    0.77
    selves
    0.76
    /'.$
    0.76
    Foto
    0.75
    ly
    0.75
    POSITIVE LOGITS
     tantalum
    1.05
     electrolyte
    1.00
     resistivity
    0.99
     capacitors
    0.97
     exporters
    0.96
     electrode
    0.94
     enthalpy
    0.94
     conductivity
    0.91
     exports
    0.89
     neodymium
    0.89
    Activations Density 0.000%

    No Known Activations