© 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. 15186
    Prev
    Next
    INDEX
    Explanations

    breach, stemmed from, top of

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

    The neuron responds to unusually rare or unexpected tokens—i.e. out-of-distribution words, punctuation marks or numbers that stand out from the surrounding text.

    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
    _
    0.84
    aryl
    0.79
    เบ
    0.77
    form
    0.75
     เบ
    0.74
    ריק
    0.74
     вопро
    0.72
    arlene
    0.71
    곁
    0.70
    beta
    0.70
    POSITIVE LOGITS
    Obviously
    0.82
     ходить
    0.81
     acabar
    0.79
    故意
    0.77
    ላቸው
    0.77
    Experts
    0.76
     souhait
    0.73
    ص
    0.71
    Researchers
    0.71
     神
    0.71
    Activations Density 0.000%

    No Known Activations