© 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. 9942
    Prev
    Next
    INDEX
    Explanations

    allow write disruption find wildly

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

    The neuron is primarily triggered by longer, multisyllabic content words.

    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
    ُ
    1.16
    ِ
    1.13
     —,
    1.10
    ،
    1.02
     –,
    1.02
    ِي
    1.01
     únicamente
    1.00
    ,/*
    1.00
    ‌,
    1.00
    Asimismo
    0.99
    POSITIVE LOGITS
    ক্রমন
    0.87
    非常的
    0.86
     kde
    0.86
     dva
    0.85
    떄
    0.83
    다라고
    0.80
     goto
    0.79
     yake
    0.77
     largement
    0.77
     কারন
    0.77
    Activations Density 0.624%

    No Known Activations