© 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. 123544
    Prev
    Next
    INDEX
    Explanations

    disguise

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

    The neuron activates on words referring to disguise or camouflage.

    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
    (
    -3.34
    B
    -2.66
    荦
    -2.42
    釤
    -2.31
    N
    -2.30
    F
    -2.27
     auft
    -2.25
    嵛
    -2.25
    V
    -2.22
    )
    -2.19
    POSITIVE LOGITS
    ’
    2.56
     voegen
    2.56
    狆
    2.53
     vertellen
    2.36
     trekken
    2.23
    
    2.19
     voeren
    2.16
     Ejecutivo
    2.13
    SocketChannel
    2.13
     voelen
    2.11
    Activations Density 0.004%

    No Known Activations