© 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. 9851
    Prev
    Next
    INDEX
    Explanations

    island geography and travel

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

    The main thing this neuron does is detect mentions of “island” (as in geographic island names or descriptions).

    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
     駅前
    -2.84
    泚
    -2.48
     tentando
    -2.42
    菒
    -2.30
    1
    -2.23
    慥
    -2.22
     incred
    -2.22
     cinquième
    -2.20
     correndo
    -2.19
    extrait
    -2.17
    POSITIVE LOGITS
    er
    2.84
    m
    2.78
    is
    2.63
     untuk
    2.44
    一番
    2.42
    t
    2.41
    d
    2.41
     für
    2.38
    u
    2.38
     должна
    2.34
    Activations Density 0.006%

    No Known Activations