© 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. 13491
    Prev
    Next
    INDEX
    Explanations

    UI elements and code structures

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

    This neuron fires on programming identifier tokens (e.g. HTML/CSS class or attribute names and other code identifiers).

    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
     moeten
    -1.26
     sempat
    -1.20
    凄く
    -1.09
    否则
    -1.09
    綺麗な
    -1.09
    irii
    -1.07
     consentimento
    -1.07
    isiaj
    -1.06
     encontraban
    -1.06
    jennifer
    -1.05
    POSITIVE LOGITS
     where
    1.48
    If
    1.13
     two
    1.05
    There
    0.99
    label
    0.98
     if
    0.98
    Do
    0.96
    Just
    0.96
    __':
    0.93
     make
    0.92
    Activations Density 0.001%

    No Known Activations