© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99439
    Prev
    Next
    INDEX
    Explanations

    local context

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

    The neuron activates on mentions of the term “local,” marking instances of the word “local” in the text.

    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
     paru
    -1.70
     bougies
    -1.64
     laine
    -1.63
    》,
    -1.61
     perles
    -1.61
     champignons
    -1.59
     tasche
    -1.55
     grec
    -1.53
     originalen
    -1.53
    岽
    -1.52
    POSITIVE LOGITS
     how
    1.98
    </strong>
    1.63
    之间
    1.51
     Ciebie
    1.50
     and
    1.42
    0
    1.41
    inafter
    1.41
     całego
    1.40
     at
    1.39
     by
    1.39
    Activations Density 0.023%

    No Known Activations