© 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. 19106
    Prev
    Next
    INDEX
    Explanations

    Turin and tion words

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

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

    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
    er
    -4.16
    ه
    -3.58
    en
    -2.72
     Sadly
    -2.69
    Although
    -2.67
    This
    -2.66
    These
    -2.64
    With
    -2.61
    曾在
    -2.59
    Even
    -2.55
    POSITIVE LOGITS
    a
    3.16
    鼍
    3.11
    
    3.03
    ING
    3.02
    牐
    2.97
    盉
    2.83
    ).
    2.73
    鱨
    2.73
    ]
    2.70
    ा
    2.70
    Activations Density 0.021%

    No Known Activations