© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6081
    Prev
    Next
    INDEX
    Explanations

    predict campaign, impact investor, parallel processing, trained weights

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

    The neuron selectively activates on 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
    y
    0.93
    et
    0.82
    het
    0.82
     
    0.80
    aa
    0.79
    ed
    0.78
    hez
    0.76
     Societies
    0.75
    el
    0.75
     Hotels
    0.74
    POSITIVE LOGITS
    요
    0.83
     추천
    0.79
    𝕡
    0.79
    アイス
    0.76
     цього
    0.75
    <0xAB>
    0.74
    ૂર્ણ
    0.74
    これで
    0.73
    리기
    0.73
     Acest
    0.72
    Activations Density 0.001%

    No Known Activations