© 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. 32823
    Prev
    Next
    INDEX
    Explanations

    doing well

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

    The neuron activates on words describing things functioning or performing effectively (e.g. “works,” “worked,” “play,” “integrate,” “serving”).

    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
     perfectly
    -1.32
    perfect
    -1.14
     perfect
    -1.08
     PERFECT
    -1.05
     perfettamente
    -1.02
     perfeito
    -1.01
     Perfectly
    -1.00
     much
    -0.99
    perfectly
    -0.98
     exactly
    -0.97
    POSITIVE LOGITS
     well
    3.00
    Well
    1.63
     хорошо
    1.62
     dobře
    1.48
    well
    1.47
     Well
    1.42
     dobrze
    1.39
     wells
    1.33
     hyvin
    1.23
     добре
    1.20
    Activations Density 0.032%

    No Known Activations