© 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. 6468
    Prev
    Next
    INDEX
    Explanations

    size comparisons

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

    The neuron fires on numeric tokens—especially decimal numbers (e.g. floating‐point 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
    וו
    0.81
    ่
    0.80
     Consequences
    0.75
    痣
    0.74
     Росії
    0.73
    ა
    0.73
     shir
    0.73
     payers
    0.73
    อฟ
    0.72
     Rxc
    0.71
    POSITIVE LOGITS
     umowy
    0.82
    olome
    0.81
    hase
    0.78
    𝘶
    0.77
     Ausstattung
    0.75
    note
    0.72
    oke
    0.72
    hest
    0.72
    lemm
    0.72
    𝘋
    0.72
    Activations Density 0.001%

    No Known Activations