© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14117
    Prev
    Next
    INDEX
    Explanations

    progress / progressive

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

    This neuron detects tokens representing floating-point numeric values (numbers with 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
     Nested
    0.77
     Add
    0.74
     Data
    0.74
    0
    0.73
     Eval
    0.72
     nested
    0.68
     Dataset
    0.67
    Account
    0.66
     En
    0.66
     Account
    0.66
    POSITIVE LOGITS
     قابلیت
    0.81
    れば
    0.80
     හා
    0.80
     sostiene
    0.80
     conoz
    0.79
    ग्रहण
    0.79
    ᱗
    0.79
    sü
    0.78
     terkenal
    0.78
     dolayı
    0.78
    Activations Density 0.000%

    No Known Activations