© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9267
    Prev
    Next
    INDEX
    Explanations

    addresses with postal codes

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

    The neuron primarily detects floating-point numbers (numeric tokens 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_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
    7
    0.77
    5
    0.76
    כ
    0.73
    8
    0.72
    6
    0.68
    9
    0.67
    2
    0.66
    CC
    0.65
    4
    0.64
    3
    0.62
    POSITIVE LOGITS
     BHK
    0.73
     corta
    0.69
     BWR
    0.67
     samen
    0.66
     quede
    0.64
     stature
    0.63
     LPTMR
    0.63
    ঞ্চলের
    0.63
     remis
    0.62
     reflectance
    0.61
    Activations Density 0.029%

    No Known Activations