© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12921
    Prev
    Next
    INDEX
    Explanations

    family:

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on mentions of font families or typeface classifications.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     recyclerView
    0.64
     councils
    0.64
    ㄺ
    0.63
     sizes
    0.62
     Sizes
    0.62
     typography
    0.62
    oplevel
    0.62
    ологии
    0.61
    ologie
    0.61
     xml
    0.60
    POSITIVE LOGITS
    Pre
    0.65
    leaning
    0.62
    Broad
    0.60
    
    0.60
    Broken
    0.58
    Blue
    0.58
    Ivy
    0.57
    Law
    0.56
    Irr
    0.56
    Le
    0.56
    Activations Density 0.001%

    No Known Activations