© 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. 59040
    Prev
    Next
    INDEX
    Explanations

    applications

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

    The neuron fires on generic product‐description phrases detailing what a device is used for (e.g. “for use in a variety of applications,” “keeps any system running smoothly,” etc.).

    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
     всички
    -0.91
    nosotros
    -0.87
     divina
    -0.86
     Beberapa
    -0.84
    hidupan
    -0.84
     türkiye
    -0.84
     ouvriers
    -0.84
     ministres
    -0.83
    Begriff
    -0.83
    pregunt
    -0.83
    POSITIVE LOGITS
     your
    1.47
     demanding
    1.20
     Anwendungen
    1.16
     users
    1.08
     applications
    1.02
    苛
    1.02
    Applications
    1.01
    applications
    1.01
     APPLICATIONS
    1.00
     workflow
    0.98
    Activations Density 0.128%

    No Known Activations