© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13455
    Prev
    Next
    INDEX
    Explanations

    last chance

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

    The neuron fires specifically on floating‐point numbers (tokens containing decimal points).

    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_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
    !\!\
    0.87
    llama
    0.82
    AR
    0.81
    cional
    0.81
    s
    0.78
    ]},
    0.77
    y
    0.77
    Ironically
    0.74
    gamma
    0.73
    #
    0.73
    POSITIVE LOGITS
    ين
    0.85
     bilder
    0.80
     Progressives
    0.80
     JTextField
    0.79
     pictures
    0.79
     गीत
    0.78
     Ł
    0.77
     Franks
    0.76
     gợi
    0.75
     قتل
    0.75
    Activations Density 0.000%

    No Known Activations