© 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. 9673
    Prev
    Next
    INDEX
    Explanations

    units of distance, measurements, and descriptive words

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

    This neuron detects numeric tokens that look like floating-point values (numbers 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
    琺
    0.79
    iterator
    0.77
    нку
    0.77
    راہیم
    0.77
    Parte
    0.76
    rée
    0.73
    ម្ម
    0.70
     Locomotive
    0.70
    インテリア
    0.70
     décor
    0.69
    POSITIVE LOGITS
    ك
    0.83
     kilometers
    0.76
     Camus
    0.75
    }$
    0.73
     أيضاً
    0.70
     SYM
    0.67
     fucking
    0.66
     centimeters
    0.66
    혹
    0.66
    大概
    0.66
    Activations Density 0.000%

    No Known Activations