© 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. 8749
    Prev
    Next
    INDEX
    Explanations

    vacation or steps

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

    The neuron is tuned to spot explicit numeric values or measurements in the text.

    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
    }^*
    0.92
    lah
    0.89
     introns
    0.87
    lated
    0.86
     AcOEt
    0.86
    }']
    0.84
    ifiers
    0.84
    }^
    0.83
    ]/
    0.82
    hesized
    0.82
    POSITIVE LOGITS
     Anmeldung
    0.73
    ت
    0.64
    o
    0.63
     apology
    0.63
     Hochzeit
    0.61
     অক্টোবর
    0.61
    ी
    0.60
     وعلى
    0.60
    ہرست
    0.60
    ي
    0.59
    Activations Density 0.000%

    No Known Activations