© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62438
    Prev
    Next
    INDEX
    Explanations

    camouflage and blending

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

    words related to camouflage and visual concealment.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron strongly activates on occurrences of the word stem “camoufl­” (as in camouflage, camouflaged, camouflaging, etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    휩
    -0.85
     Recycled
    -0.82
     administración
    -0.79
     communautaire
    -0.79
     żół
    -0.78
     zwarte
    -0.78
    ゴン
    -0.77
    IFICATION
    -0.77
    ּוֹ
    -0.75
    タック
    -0.75
    POSITIVE LOGITS
     camouflage
    2.13
     camuf
    1.46
     Cam
    1.45
     camo
    1.38
     cam
    1.33
    cam
    1.27
     disruptive
    1.20
     concealment
    1.19
     маски
    1.14
    camo
    1.09
    Activations Density 0.015%

    No Known Activations