© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49688
    Prev
    Next
    INDEX
    Explanations

    how things are configured or described

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

    The neuron fires on words bearing the common German adjective/adverbial ending “-lich” or the English “-ly” suffix.

    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
     gave
    -0.92
     quite
    -0.89
     primarily
    -0.88
     showed
    -0.85
     didn
    -0.84
     использова
    -0.84
    kritik
    -0.84
    chränkungen
    -0.83
    がございます
    -0.83
     probably
    -0.82
    POSITIVE LOGITS
     worded
    1.37
     behaving
    1.17
     disposed
    1.14
     oriented
    1.13
     configured
    1.13
     behaved
    1.04
    aliyet
    1.02
     interrelated
    0.99
     construed
    0.99
     arranged
    0.98
    Activations Density 0.046%

    No Known Activations