© 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. 1904
    Prev
    Next
    INDEX
    Explanations

    Prague and exemplified

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

    The neuron activates on occurrences of the place name “Prague.”

    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
    拶
    -3.59
    饪
    -3.38
    没问题
    -3.34
    擽
    -3.33
    謦
    -3.13
    悫
    -3.05
    鲧
    -3.00
     aborto
    -2.98
    镡
    -2.94
    ౧
    -2.92
    POSITIVE LOGITS
    er
    3.47
    E
    3.31
    In
    3.30
    *
    3.30
    —
    3.13
    .
    3.11
    e
    3.09
    0
    3.00
    V
    2.98
    1
    2.95
    Activations Density 0.002%

    No Known Activations