© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11653
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on mentions of “view” or “views” (i.e. descriptions of scenic outlooks).

    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
    kannya
    1.00
    ления
    0.99
    kilometer
    0.95
    IZED
    0.95
     glows
    0.94
    ى
    0.92
    ীর
    0.91
    แสง
    0.90
    িয়া
    0.88
    부분
    0.88
    POSITIVE LOGITS
    ord
    0.83
    HasStarred
    0.80
    お得
    0.78
    ö
    0.78
    い
    0.77
    に応じて
    0.75
    ू
    0.74
     शपथ
    0.73
     க்கு
    0.73
     xét
    0.72
    Activations Density 0.006%

    No Known Activations