© 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. 34-GEMMASCOPE-RES-131K
    7. 48469
    Prev
    Next
    INDEX
    Explanations

    domain names or TLDs

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

    The neuron strongly activates on the literal period “.” used as a separator (e.g. in filenames, domain names, version or CWE numbers).

    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
     Parfum
    -1.01
     ducati
    -0.90
     tarif
    -0.90
     Enti
    -0.89
     Pende
    -0.88
    的味道
    -0.88
     uhd
    -0.87
     Isol
    -0.86
    蘚
    -0.85
     degust
    -0.85
    POSITIVE LOGITS
     (;;)
    0.97
     recientes
    0.94
     wiederum
    0.93
    ymmetry
    0.93
     aqueles
    0.91
    Recently
    0.90
    ).__
    0.90
     especializados
    0.89
    (;;)
    0.89
     caratter
    0.88
    Activations Density 0.040%

    No Known Activations