© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75440
    Prev
    Next
    INDEX
    Explanations

    names Francisco and Francesco

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

    The neuron activates strongly on the token “Francisco” (and more weakly on related personal‐name tokens like “Antonio”), i.e. it detects occurrences of that proper name.

    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
     unſ
    -2.86
     
    -2.63
     désir
    -2.61
     were
    -2.42
     Perſ
    -2.39
     crippled
    -2.28
     :.
    -2.28
     mépris
    -2.27
     myriad
    -2.25
     Inſ
    -2.25
    POSITIVE LOGITS
     untuk
    2.59
    鴒
    2.50
    鴣
    2.50
    𓆜
    2.47
     для
    2.47
    providedIn
    2.45
    .
    2.42
     ''){
    2.42
    })
    2.38
     }));
    2.28
    Activations Density 0.006%

    No Known Activations