© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6135
    Prev
    Next
    INDEX
    Explanations

    arrays and lists

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

    The neuron is tuned to pick up tokens that are stray floating‐point numbers (i.e. numeric values with decimals) in the text.

    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
     אחר
    0.72
     Fortune
    0.71
     Reproduction
    0.67
    કી
    0.66
    चित
    0.64
     Controversy
    0.64
    屽
    0.63
     insights
    0.63
    ಾ
    0.63
     Borrower
    0.63
    POSITIVE LOGITS
    plein
    0.98
     nettoyer
    0.96
    sede
    0.95
     бола
    0.95
    bereich
    0.94
    잼
    0.92
    clonal
    0.90
    lukan
    0.89
    steroidal
    0.89
    sy
    0.88
    Activations Density 0.000%

    No Known Activations