© 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. 14712
    Prev
    Next
    INDEX
    Explanations

    evidence against the thought

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

    The neuron primarily detects numeric tokens, especially decimal numbers.

    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
    سته
    0.79
    cte
    0.79
     дроб
    0.75
     attent
    0.75
    תיים
    0.74
    }=
    0.74
     conceded
    0.74
    ส์
    0.73
    主角
    0.70
    তনের
    0.70
    POSITIVE LOGITS
     Songs
    0.77
     Clinic
    0.74
    <b>
    0.74
    <0x80>
    0.73
    camp
    0.73
    ebay
    0.73
    என
    0.71
    তীশ
    0.71
    c
    0.71
    ढ़ाई
    0.70
    Activations Density 0.001%

    No Known Activations