© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12455
    Prev
    Next
    INDEX
    Explanations

    `Location B`, `Speaker B`, `Bag B`

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

    The neuron specifically detects decimal numbers (floating‐point numeric tokens).

    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_31_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
    ২
    0.79
     ২
    0.72
    3
    0.69
    ۲
    0.69
    ১
    0.66
    
    0.65
    2
    0.63
    ೩
    0.63
    𝟮
    0.63
    𝟯
    0.63
    POSITIVE LOGITS
     essayer
    0.55
     czym
    0.54
     gaye
    0.52
     entretien
    0.52
     b
    0.51
     frequentemente
    0.51
     Charles
    0.50
     giallo
    0.50
     karan
    0.49
    ിക്കുകയും
    0.49
    Activations Density 0.030%

    No Known Activations