© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104385
    Prev
    Next
    INDEX
    Explanations

    locations and events

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

    The neuron fires on words and phrases that denote looking, seeing, or attending—e.g. “look,” “view,” “site visits,” “watch,” and similar terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -1.77
     I
    -1.74
    R
    -1.59
    th
    -1.53
    <b>
    -1.51
    the
    -1.49
     which
    -1.41
    o
    -1.41
    S
    -1.37
    er
    -1.36
    POSITIVE LOGITS
     the
    1.97
    
    1.77
     gedrag
    1.59
    tuy
    1.55
    
    1.53
    kém
    1.52
    Câ
    1.45
    Mua
    1.41
    tuto
    1.41
    modellen
    1.41
    Activations Density 0.019%

    No Known Activations