© 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. 12033
    Prev
    Next
    INDEX
    Explanations

    Stable Diffusion BlueWillow

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

    The neuron is keyed to detect numeric tokens and numeric expressions (e.g. grade levels, dates, times).

    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
    Acknowledg
    0.75
     लड़की
    0.73
    ոն
    0.71
     미국
    0.71
    nesota
    0.70
    美国
    0.70
    AspectRatio
    0.69
    ☮
    0.69
     굉장히
    0.68
     꼭
    0.67
    POSITIVE LOGITS
     অর্থাৎ
    0.81
     maupun
    0.80
     অথবা
    0.76
     or
    0.73
     arba
    0.73
     или
    0.72
     veya
    0.71
     movers
    0.71
     atau
    0.70
     eller
    0.69
    Activations Density 0.728%

    No Known Activations