© 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. 22-GEMMASCOPE-RES-131K
    4. 130837
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on longer, multi-syllable content words (often mid-frequency or uncommon nouns and adjectives).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    compound nouns or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    4
    -1.72
     支援
    -1.70
    メニューは
    -1.65
    3
    -1.64
    Ilustra
    -1.55
    ٩
    -1.55
    Rumah
    -1.52
    いたします
    -1.50
    Interes
    -1.48
    お話
    -1.47
    POSITIVE LOGITS
    olge
    1.79
    romeda
    1.77
    PasswordEncoder
    1.71
    撂
    1.70
    ༷
    1.68
    strator
    1.66
    licitud
    1.64
    方も
    1.58
    thodox
    1.58
     a
    1.57
    Activations Density 0.220%

    No Known Activations