© 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. 3086
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on uncommon Capitalized tokens—i.e. proper names and other named‐entity words.

    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
    0.85
     if
    0.65
     int
    0.57
     N
    0.56
     tego
    0.55
     Triton
    0.55
     K
    0.55
     t
    0.54
     tilted
    0.54
     f
    0.54
    POSITIVE LOGITS
    ol
    0.66
    attenzione
    0.65
    atani
    0.65
    órica
    0.64
    uña
    0.64
    atual
    0.63
    तिहास
    0.63
    oléon
    0.63
    at
    0.62
    ównie
    0.62
    Activations Density 0.000%

    No Known Activations