© 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. 12445
    Prev
    Next
    INDEX
    Explanations

    's or "s" followed by relevant words

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

    The neuron activates on numeric tokens, especially floating-point numbers (i.e. digits containing a decimal point).

    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
     globales
    0.75
    Weiter
    0.72
    렴
    0.70
    演讲
    0.69
    #!/
    0.68
    learn
    0.67
     владе
    0.67
    잠
    0.66
    ;&
    0.65
    Tecla
    0.64
    POSITIVE LOGITS
     barometer
    0.84
     Gods
    0.78
     cij
    0.77
     flowchart
    0.77
     bomber
    0.76
    കൻ
    0.75
    ছাড়া
    0.75
    ギン
    0.74
     citadel
    0.74
     previewBuilder
    0.73
    Activations Density 0.000%

    No Known Activations