© 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. 12905
    Prev
    Next
    INDEX
    Explanations

    word endings

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

    The main thing this neuron does is detect numeric tokens or numerical values (e.g., integers, decimals, codes).

    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
    们
    0.41
    могою
    0.40
    олові
    0.40
    чением
    0.39
    ުޅ
    0.38
    燚
    0.38
    νοντας
    0.38
    acelet
    0.38
    роки
    0.37
    ERATE
    0.37
    POSITIVE LOGITS
     kommen
    0.40
     l
    0.39
     tien
    0.39
    es
    0.38
     nessun
    0.38
     have
    0.38
     hanno
    0.38
     plaats
    0.38
     zes
    0.37
     têm
    0.37
    Activations Density 0.008%

    No Known Activations