© 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. 2328
    Prev
    Next
    INDEX
    Explanations

    explain or reveal

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

    The neuron activates on numeric tokens—especially multi‐digit and decimal numbers.

    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
     করলেও
    0.75
     لأنه
    0.73
     bisschen
    0.71
    pesar
    0.68
     গুলো
    0.68
    썻
    0.68
     থাকলেও
    0.67
     uptick
    0.67
    咋
    0.67
    ᵔ
    0.67
    POSITIVE LOGITS
     within
    1.40
     therein
    1.40
     in
    1.26
     at
    1.24
     dalam
    1.23
     katika
    1.20
     henceforth
    1.18
     herewith
    1.18
     therefrom
    1.17
     forthwith
    1.17
    Activations Density 0.621%

    No Known Activations