© 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. 15261
    Prev
    Next
    INDEX
    Explanations

    low or moderate

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

    The neuron consistently fires on the very first content word in a new paragraph or block of 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
    犹
    0.76
    ism
    0.75
    Toxic
    0.74
    Particular
    0.71
    السلام
    0.70
    ’
    0.70
    ikiran
    0.70
    Par
    0.68
    Title
    0.68
    '
    0.68
    POSITIVE LOGITS
     pyrolysis
    0.99
     コ
    0.92
     ン
    0.89
     norepinephrine
    0.89
     쇼
    0.88
     gruppo
    0.88
     compañeros
    0.86
     భాగంగా
    0.86
     vía
    0.85
     レッド
    0.84
    Activations Density 0.000%

    No Known Activations