© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6963
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words that look like section or document titles/headers (e.g. “IE7,” “FriendFeed,” “Dangerous Goods,” “Metabolism,” etc.).

    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
    D
    0.86
     Motor
    0.86
    S
    0.85
    P
    0.83
    or
    0.81
    J
    0.81
    น้อง
    0.78
     pesta
    0.77
    Y
    0.75
    motor
    0.75
    POSITIVE LOGITS
     entière
    0.82
    IENT
    0.74
     prosciutto
    0.74
     chimique
    0.69
    ्वती
    0.68
    лно
    0.68
     particulier
    0.66
    ções
    0.65
    앉
    0.65
    Mexican
    0.64
    Activations Density 0.000%

    No Known Activations