© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15197
    Prev
    Next
    INDEX
    Explanations

    ForegroundColor Green

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

    The main thing this neuron does is detect the period punctuation mark (full stop).

    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
    𝐩
    0.85
     teks
    0.82
     dehuman
    0.79
    ▂
    0.79
     tekst
    0.77
     TextAlign
    0.77
    衽
    0.75
     plainly
    0.74
     ligature
    0.73
     طریقے
    0.73
    POSITIVE LOGITS
    ти
    0.88
    D
    0.75
    ى
    0.74
    C
    0.73
    6
    0.71
    cia
    0.70
     avril
    0.70
    ઇ
    0.70
    yil
    0.69
    ianz
    0.68
    Activations Density 0.002%

    No Known Activations