© 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. 75583
    Prev
    Next
    INDEX
    Explanations

    Dear Sir's

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

    The neuron flags tokens that are programming or configuration identifiers (e.g. JSON field names or code property names).

    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
     all
    -1.11
    𖡼
    -1.07
    cassandra
    -1.05
     on
    -1.02
     without
    -1.00
    redient
    -0.90
     every
    -0.88
    配慮
    -0.88
    rettet
    -0.86
     minde
    -0.86
    POSITIVE LOGITS
     fréquemment
    1.09
    decre
    1.03
     posiblemente
    1.02
     possibilidade
    1.00
     específicamente
    0.96
     attacco
    0.95
     hilfiger
    0.95
    跟你
    0.93
     JLabel
    0.91
    比如说
    0.90
    Activations Density 0.000%

    No Known Activations