© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9652
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting floating-point numeric tokens (numbers with decimal points).

    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
    это
    0.70
    с
    0.66
    ();
    0.66
    this
    0.66
    Н
    0.66
    Л
    0.66
     or
    0.65
    sin
    0.65
    %,
    0.65
    它
    0.64
    POSITIVE LOGITS
    inairement
    0.76
     високо
    0.71
     بیشتر
    0.70
     fanbase
    0.70
     possibilité
    0.68
     ventilator
    0.68
     nécessité
    0.67
     احتيا
    0.66
     nombreux
    0.66
     broader
    0.66
    Activations Density 0.000%

    No Known Activations