© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4189
    Prev
    Next
    INDEX
    Explanations

    ADDRESS

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

    The neuron strongly responds to line‐break characters (e.g. “\n” and “\” tokens), i.e. document formatting newlines.

    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
    im
    1.01
    o
    0.89
    upport
    0.89
    ub
    0.86
    p
    0.83
    in
    0.82
    i
    0.80
    al
    0.79
    oq
    0.79
    ie
    0.78
    POSITIVE LOGITS
    ляем
    0.76
     meh
    0.72
    はず
    0.71
    やった
    0.71
     Terror
    0.70
    ляю
    0.69
    긋
    0.68
    𝗗
    0.67
     Kumb
    0.66
    𝑻
    0.65
    Activations Density 0.040%

    No Known Activations