© 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. 34-GEMMASCOPE-RES-131K
    7. 38290
    Prev
    Next
    INDEX
    Explanations

    academic or technical terms

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

    The neuron is specialized to fire on the exact token “part.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ρά
    -0.88
     onsdag
    -0.83
     cashier
    -0.83
     idées
    -0.81
     melakukannya
    -0.79
     membag
    -0.79
     RouterModule
    -0.79
    𝟓
    -0.79
     menghubungi
    -0.77
    粉絲
    -0.77
    POSITIVE LOGITS
    andan
    0.85
    private
    0.84
     private
    0.84
    ändigt
    0.82
     Mis
    0.81
     acompaña
    0.79
     Каза
    0.77
     global
    0.77
     perpetual
    0.76
     princípio
    0.75
    Activations Density 0.000%

    No Known Activations