© 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. 75036
    Prev
    Next
    INDEX
    Explanations

    string literals and code identifiers

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

    The neuron consistently lights up on tokens that appear inside literal quotation marks (single or double quotes) in code or error messages.

    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
    肮
    -1.69
     большинстве
    -1.49
    Just
    -1.45
     schreibt
    -1.39
    Often
    -1.38
     тях
    -1.35
     рабочей
    -1.35
    attaque
    -1.34
    Make
    -1.34
    ----
    -1.33
    POSITIVE LOGITS
     have
    2.22
     of
    1.89
     However
    1.74
     Ancak
    1.64
    ﻂ
    1.59
     procedure
    1.57
     we
    1.49
    思议
    1.48
     are
    1.48
    warte
    1.41
    Activations Density 0.010%

    No Known Activations