© 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. 65488
    Prev
    Next
    INDEX
    Explanations

    see followed by reference

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

    The neuron activates on occurrences of “see” in reference or citation contexts.

    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
     ihre
    -2.31
     (
    -2.23
     más
    -2.16
    t
    -2.08
     
    -2.08
     to
    -2.06
     barring
    -2.05
     eventual
    -2.05
     my
    -2.03
    “
    -2.02
    POSITIVE LOGITS
    ‪.‬‬
    3.31
    Ruju
    3.20
    硨
    2.92
     ſch
    2.81
     zoude
    2.75
    ⢎
    2.63
     alamu
    2.61
    鲧
    2.59
     古风
    2.48
    
    2.48
    Activations Density 0.024%

    No Known Activations