© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5992
    Prev
    Next
    INDEX
    Explanations

    car

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

    The neuron strongly activates on decimal‐style numbers (e.g. volume/issue/page citations).

    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
    きれい
    0.87
     sarees
    0.86
    耇
    0.84
    ᄊ
    0.82
     listop
    0.81
    \}$
    0.80
     žmon
    0.80
     použití
    0.80
     zari
    0.79
     monatomic
    0.79
    POSITIVE LOGITS
    ll
    0.84
    lt
    0.76
    ly
    0.74
    ller
    0.74
    rific
    0.73
    tains
    0.73
    த்திற்கு
    0.72
     borders
    0.70
    kD
    0.69
    v
    0.69
    Activations Density 0.000%

    No Known Activations