© 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. 8515
    Prev
    Next
    INDEX
    Explanations

    legacy systems, application, completed, scale, days

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

    The neuron fires on very common, mid‐frequency English words (e.g. “feel,” “sports,” “same,” “works”).

    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
    ёг
    0.92
    f
    0.92
     damal
    0.89
    gi
    0.84
     puertos
    0.83
    gc
    0.82
     intérpre
    0.82
    os
    0.81
     ኢ
    0.81
     pulgadas
    0.78
    POSITIVE LOGITS
    ፈል
    0.76
    Jenis
    0.73
    Bien
    0.67
    ريع
    0.66
    Fone
    0.66
    Agree
    0.65
    Bolt
    0.65
    ริญ
    0.65
     який
    0.65
    Face
    0.64
    Activations Density 0.000%

    No Known Activations