© 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. 8921
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numerical tokens representing decimal numbers (i.e. floating-point numerals).

    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
     Paid
    0.79
    s
    0.74
     Entries
    0.71
    ії
    0.69
     Chairs
    0.68
     Individuals
    0.66
     Eğ
    0.66
    0
    0.66
    ين
    0.65
     Pump
    0.65
    POSITIVE LOGITS
    товой
    0.87
     detach
    0.84
     fuselage
    0.84
    товый
    0.84
     небольшой
    0.80
    ʄ
    0.80
    อฟ
    0.78
     разнови
    0.78
     சிறிய
    0.77
     pequeño
    0.76
    Activations Density 0.000%

    No Known Activations