© 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. 6005
    Prev
    Next
    INDEX
    Explanations

    blanks in questions

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

    The neuron fires on underscore‐only tokens (blank fill‐in‐the‐blank placeholders).

    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
    QString
    0.79
    WebApplication
    0.75
    Wendy
    0.71
    trivial
    0.70
    M
    0.70
    B
    0.70
    mx
    0.69
    RecyclerView
    0.68
    U
    0.68
    title
    0.67
    POSITIVE LOGITS
     facilitates
    0.81
     underpinning
    0.78
     fosters
    0.77
     volts
    0.77
     booms
    0.74
     canaux
    0.74
     empowers
    0.73
     blocs
    0.73
     vertebrates
    0.72
     enforces
    0.72
    Activations Density 0.000%

    No Known Activations