© 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. 44736
    Prev
    Next
    INDEX
    Explanations

    LOS Angeles

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

    This neuron fires on the uppercase string “LOS,” as in the start of “LOS ANGELES” datelines.

    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
    ܆
    -2.72
    慙
    -2.67
    }
    -2.48
    with
    -2.41
     aspire
    -2.39
    $
    -2.31
    the
    -2.30
    蛻
    -2.25
    킁
    -2.23
    ής
    -2.20
    POSITIVE LOGITS
    觏
    3.00
    
    2.50
     to
    2.34
    蕯
    2.23
     surpassed
    2.16
    tedrale
    2.16
    攫
    2.14
     dubbed
    2.14
     It
    2.13
    ("")]
    2.11
    Activations Density 0.001%

    No Known Activations