© 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. 1658
    Prev
    Next
    INDEX
    Explanations

    commands following 'run' or 'type'

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

    The neuron fires on numeric tokens (especially floating‐point numbers).

    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
    ருடன்
    0.55
    úa
    0.54
    স্তি
    0.53
    astas
    0.51
     규
    0.51
    iggins
    0.50
    aria
    0.50
    যু
    0.50
    莽
    0.49
    த்ரே
    0.49
    POSITIVE LOGITS
     kepada
    0.69
     wisata
    0.68
     LIKE
    0.68
     seguenti
    0.68
     kotak
    0.66
     няко
    0.66
     lembaga
    0.65
     seperti
    0.64
     paiement
    0.63
     herhangi
    0.62
    Activations Density 0.003%

    No Known Activations