© 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. 14031
    Prev
    Next
    INDEX
    Explanations

    listing options or continuations

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

    This neuron strongly activates on numeric tokens (e.g. years, page numbers, citation IDs, or other digit-containing strings).

    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
     pacing
    0.78
    フォー
    0.76
    を開
    0.73
    ケ
    0.73
    エース
    0.73
    択
    0.72
     rzeczy
    0.72
    覚え
    0.71
     ktore
    0.70
    あらゆる
    0.70
    POSITIVE LOGITS
     很
    0.80
    er
    0.76
    ب
    0.74
     长
    0.73
    త
    0.73
    ্ধে
    0.72
    很
    0.72
    س
    0.71
    ệnh
    0.70
     traitement
    0.70
    Activations Density 0.000%

    No Known Activations