© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    african countries and cities

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

    This neuron detects numeric expressions and figures—especially years, budget amounts, and other multi­digit or monetary values.

    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
     (
    1.13
     +
    1.09
     =
    0.99
     uses
    0.93
     -
    0.93
     used
    0.93
     Né
    0.90
     (=
    0.90
     \
    0.89
     원래
    0.89
    POSITIVE LOGITS
    Niger
    1.44
     Alhaji
    1.38
     Enugu
    1.34
     Abia
    1.30
     Kaduna
    1.29
     Ondo
    1.28
     Ekiti
    1.28
     Jumat
    1.27
     Anambra
    1.27
    Nigeria
    1.23
    Activations Density 0.322%

    No Known Activations