© 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. 13450
    Prev
    Next
    INDEX
    Explanations

    change of state or removal

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

    The neuron responds to numeric expressions and measurements (e.g. quantities, percentages, dosages, years).

    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
     entertainers
    0.65
     обслужи
    0.63
     социальных
    0.63
     mathbf
    0.62
     managable
    0.61
     wollen
    0.61
    nants
    0.60
    챙
    0.59
    쥔
    0.59
     sociais
    0.58
    POSITIVE LOGITS
     grafting
    1.18
     sublimation
    1.11
     extrusion
    1.05
     incineration
    0.99
     tunneling
    0.98
    Substitution
    0.98
     Substitution
    0.98
     tunnelling
    0.98
     irradiation
    0.97
     bribery
    0.96
    Activations Density 0.706%

    No Known Activations