© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 1974
    Prev
    Next
    INDEX
    Explanations

    The neuron flags narrative plot‐driven passages—i.e. sequences describing characters, actions, and events in a story.

    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
     I
    1.04
     
    1.04
     today
    1.02
     this
    1.01
     said
    1.01
     number
    1.01
     if
    1.00
     we
    0.98
     i
    0.98
     width
    0.97
    POSITIVE LOGITS
     дочь
    1.20
     തന്റെ
    1.17
    قتل
    1.05
     ඔහුගේ
    1.05
     అతని
    1.05
     ඔහු
    1.04
     пытается
    1.04
     قتل
    1.02
     അന്വേഷ
    1.02
    PARATION
    1.02
    Activations Density 0.778%

    No Known Activations