© 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. 2951
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

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

    The neuron activates on numeric tokens and number-like expressions (e.g. multi‐digit figures and decimals).

    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
    *
    0.52
    anzitutto
    0.50
    ie
    0.48
     Yum
    0.47
     Ağustos
    0.47
     Анти
    0.46
    Early
    0.46
     Within
    0.46
     編
    0.46
     Oscillator
    0.46
    POSITIVE LOGITS
     суще
    0.45
     más
    0.42
     unbeatable
    0.40
     matchs
    0.40
    较为
    0.40
     undeniably
    0.40
     తా
    0.39
     venced
    0.38
     tuple
    0.38
     weit
    0.38
    Activations Density 0.000%

    No Known Activations