© 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. 49245
    Prev
    Next
    INDEX
    Explanations

    restore power, energy, or HP

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

    The neuron fires on numeric values and quantitative parameters (numbers, percentages, and stat‐related tokens) in the text.

    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
     März
    -0.85
     Wikiquote
    -0.82
     Maschine
    -0.78
    gares
    -0.77
     KeyError
    -0.77
    dB
    -0.77
    ónio
    -0.76
    asilkan
    -0.74
     mengh
    -0.74
    тьми
    -0.73
    POSITIVE LOGITS
     regenerate
    1.38
     regener
    1.38
     regeneration
    1.34
     replenish
    1.33
     energy
    1.24
     reserve
    1.24
     replen
    1.23
     restore
    1.22
     mana
    1.22
     restores
    1.20
    Activations Density 0.009%

    No Known Activations