© 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. 22-GEMMASCOPE-RES-131K
    7. 95334
    Prev
    Next
    INDEX
    Explanations

    user roles permissions actions

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

    The neuron flags programming‐style identifiers and keywords (e.g. variable, class, module, and import names) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     celebridades
    -1.37
     sezonu
    -1.23
     forskning
    -1.22
     katastro
    -1.22
     muñecas
    -1.21
     kalori
    -1.20
    Abbiamo
    -1.17
     kalend
    -1.16
    alanta
    -1.15
     princesas
    -1.14
    POSITIVE LOGITS
    镀
    1.14
     塗装
    1.08
    问问
    1.03
     unve
    1.00
    asha
    0.97
    きました
    0.94
    棻
    0.94
    ánico
    0.94
     wpły
    0.94
    Ephesians
    0.93
    Activations Density 0.024%

    No Known Activations