© 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. 6922
    Prev
    Next
    INDEX
    Explanations

    This neuron specializes in spotting mentions of waterfront (water-edge) locations or properties.

    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
    lly
    0.71
    Paragraph
    0.70
     excret
    0.69
     MFG
    0.69
    GridLayout
    0.66
    แค่
    0.64
     fich
    0.64
    窿
    0.64
     offence
    0.63
    lf
    0.63
    POSITIVE LOGITS
    летие
    0.76
    大海
    0.74
     continúa
    0.74
    atorios
    0.73
    не
    0.73
    رهای
    0.73
    绘画
    0.71
     anunció
    0.71
    أ
    0.71
    atori
    0.70
    Activations Density 0.000%

    No Known Activations