© 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. 10-GEMMASCOPE-RES-131K
    7. 9110
    Prev
    Next
    INDEX
    Explanations

    technical terms and code

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

    The neuron fires on programming identifiers and API/class names (e.g. function, class, variable, and type 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_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
     Though
    -1.64
     Although
    -1.54
     While
    -1.46
     However
    -1.41
    Though
    -1.40
     Despite
    -1.37
     Perhaps
    -1.32
     Throughout
    -1.31
     Maybe
    -1.27
     can
    -1.26
    POSITIVE LOGITS
     Eſ
    1.58
    僰
    1.30
     ['./
    1.25
     mauva
    1.23
    dits
    1.22
     nke
    1.20
    鶿
    1.20
     菇
    1.19
    艄
    1.19
     choses
    1.17
    Activations Density 0.547%

    No Known Activations