© 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. 12660
    Prev
    Next
    INDEX
    Explanations

    semiconductor devices and networks

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

    The neuron fires on specialized technical or domain-specific terms (e.g. jargon from patents, computer networking, electronics, 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_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
     hatta
    -1.58
     verschillende
    -1.57
     possono
    -1.52
     '{@
    -1.50
     mehreren
    -1.49
     dacă
    -1.48
     hebben
    -1.45
     USING
    -1.45
     méthodes
    -1.43
     Frankrijk
    -1.43
    POSITIVE LOGITS
     and
    2.00
     while
    1.70
     with
    1.70
    These
    1.65
    While
    1.50
    They
    1.49
    Other
    1.48
    Those
    1.47
     While
    1.41
    With
    1.40
    Activations Density 0.206%

    No Known Activations