© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1786
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (years, digits) and uppercase or alphanumeric sequences (acronyms, codes, initials).

    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_31_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
     Series
    0.68
     Virus
    0.64
     Theatre
    0.61
     Completion
    0.61
     Ride
    0.60
     p
    0.59
     Tribute
    0.59
     FIXME
    0.59
     Recipe
    0.59
     Perfection
    0.58
    POSITIVE LOGITS
     estadounidenses
    0.83
    ˗
    0.72
    十大
    0.71
     /ˈ
    0.71
     американ
    0.70
    
    0.70
    古代
    0.68
    世界の
    0.67
     ανθρώ
    0.67
    世界上最大的
    0.66
    Activations Density 0.348%

    No Known Activations