© 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. 8537
    Prev
    Next
    INDEX
    Explanations

    frequency vs scale

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

    This neuron primarily detects numerical tokens—especially measurements, decimal numbers, and quantities.

    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
    ละคร
    0.76
    apayati
    0.73
    County
    0.73
    蒨
    0.72
    لاميذ
    0.70
    Siempre
    0.69
    Atlanta
    0.68
    ayena
    0.68
    httparty
    0.68
    динку
    0.68
    POSITIVE LOGITS
     phonons
    0.88
     dependences
    0.88
     probed
    0.85
     diodes
    0.85
     quasip
    0.85
     photonic
    0.82
     birefringence
    0.82
     renormalized
    0.81
    ≳
    0.81
    ≲
    0.80
    Activations Density 0.010%

    No Known Activations