© 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. 22-GEMMASCOPE-RES-131K
    7. 69069
    Prev
    Next
    INDEX
    Explanations

    power and strength

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

    The neuron detects descriptions of armor-piercing or penetration performance (e.g., how thick armor a weapon can pierce).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ütün
    -1.02
    englisch
    -0.94
    ngilizce
    -0.93
     mecánica
    -0.83
    intellij
    -0.83
     скла
    -0.83
    áles
    -0.83
    鎵
    -0.82
    learner
    -0.82
     Nationen
    -0.82
    POSITIVE LOGITS
     powerful
    1.27
     strength
    1.23
     overpowered
    1.12
     stronger
    1.05
     мощ
    1.04
     powered
    0.99
     strongest
    0.98
     power
    0.97
    powerful
    0.96
     powerhouse
    0.95
    Activations Density 0.091%

    No Known Activations