© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11727
    Prev
    Next
    INDEX
    Explanations

    biotechnology. ocean wide. Grandmother's. rows. proximity

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

    The neuron selectively activates on decimal numbers (numeric tokens containing a dot and digits).

    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
    2
    0.83
    3
    0.83
    5
    0.81
    7
    0.80
    ią
    0.79
    į
    0.79
    itr
    0.79
    8
    0.77
    </
    0.76
    1
    0.75
    POSITIVE LOGITS
    वरणीय
    0.81
    नोमियल
    0.80
    çon
    0.79
     Hôtel
    0.78
    ہنی
    0.78
    艨
    0.77
    評價
    0.75
     Branche
    0.74
     Elijah
    0.73
    िटीज
    0.73
    Activations Density 0.000%

    No Known Activations