© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6478
    Prev
    Next
    INDEX
    Explanations

    rewarded, pricing, Great, pain, sign

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

    The neuron fires on numeric tokens representing measurement or score values (especially decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    product reviews

    np_max-act · claude-4-5-sonnetTriggered by @jrosseruk
    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
     nhóm
    0.79
     Gynecol
    0.73
     กลุ่ม
    0.70
     หมู่
    0.70
     Sakai
    0.70
    ❒
    0.70
     Democr
    0.69
     erstmals
    0.69
     Deuteronomy
    0.69
     Pediatr
    0.69
    POSITIVE LOGITS
    шу
    0.68
    луу
    0.64
    栲
    0.61
    丰富
    0.60
    高
    0.60
     väga
    0.59
     winding
    0.59
    низ
    0.59
    數量
    0.58
    gradient
    0.58
    Activations Density 0.000%

    No Known Activations