© 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. 34-GEMMASCOPE-RES-131K
    7. 65493
    Prev
    Next
    INDEX
    Explanations

    NOT FOR PUBLICATION FILED

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

    The neuron fires on the literal “.” (dot) used as an operator in code (e.g. in method‐call chains).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ťa
    -0.80
    Bitch
    -0.79
     جمهور
    -0.78
     simplesmente
    -0.78
    ulica
    -0.73
    　　……
    -0.73
     IQ
    -0.72
    頓
    -0.72
     Krankenhaus
    -0.72
    ihnach
    -0.71
    POSITIVE LOGITS
     mélanger
    0.87
    ↕
    0.81
     erreich
    0.79
     мысли
    0.77
     tân
    0.76
     спів
    0.76
    儸
    0.75
    Rif
    0.73
     frenos
    0.73
    gely
    0.73
    Activations Density 0.002%

    No Known Activations