© 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. 14189
    Prev
    Next
    INDEX
    Explanations

    Lima, Peru, or Adriana Lima

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

    The neuron is triggered by the string “lima,” strongly marking the place‐name “Lima” (and more weakly the same letter sequence embedded in other words).

    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
    2
    -3.98
    3
    -3.52
    1
    -3.52
    9
    -3.05
    6
    -3.03
    4
    -3.02
    P
    -2.94
    7
    -2.94
    We
    -2.94
    L
    -2.91
    POSITIVE LOGITS
     撮っ
    3.11
    隄
    2.73
     During
    2.56
     Comprometido
    2.52
    ization
    2.48
    ва
    2.34
     When
    2.28
    三日
    2.27
     considérons
    2.22
    墙壁
    2.22
    Activations Density 0.006%

    No Known Activations