© 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. 66150
    Prev
    Next
    INDEX
    Explanations

    pointer related to mouse or cursor

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

    The neuron activates on occurrences of the token “pointer.”

    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
     a
    -2.33
     Welche
    -1.76
     of
    -1.76
     inizio
    -1.69
     acusa
    -1.55
    蜴
    -1.52
     intric
    -1.44
    ()?;
    -1.43
     arid
    -1.43
    .'
    -1.43
    POSITIVE LOGITS
     Légion
    1.68
    𓋼
    1.63
    纯粹
    1.55
    蒹
    1.53
    All
    1.51
    s
    1.50
    you
    1.49
     all
    1.45
    $
    1.44
    慙
    1.44
    Activations Density 0.001%

    No Known Activations