© 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. 11646
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized to pick up on large floating-point numeric tokens (e.g. “1287.3402,” “1287.712,” etc.).

    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
    sill
    0.78
    at
    0.71
    iare
    0.71
     U
    0.70
     d
    0.70
     seperti
    0.69
    silk
    0.69
    ম
    0.69
    sila
    0.67
     וש
    0.67
    POSITIVE LOGITS
    чную
    0.86
    攣
    0.82
    킁
    0.81
    чным
    0.80
     controle
    0.80
    ション
    0.79
     psicología
    0.78
     Vorteil
    0.77
    ことが
    0.76
    чная
    0.75
    Activations Density 0.000%

    No Known Activations