© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31461
    Prev
    Next
    INDEX
    Explanations

    achieving liberation and transformation

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

    The neuron activates on abstract nouns naming transformative change processes—e.g. redemption, reform, empowerment, emancipation, awakening, self-realization—indicating it’s looking for words that denote liberation or spiritual/moral renewal.

    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
    良いです
    -0.92
    かき
    -0.84
     XCTest
    -0.80
    سته
    -0.77
    created
    -0.77
    őre
    -0.75
    Loy
    -0.75
    color
    -0.74
    get
    -0.73
     decides
    -0.73
    POSITIVE LOGITS
     through
    1.28
     of
    1.16
    enment
    1.02
     Through
    1.02
     achieved
    0.98
    анс
    0.94
    ination
    0.93
     через
    0.92
     melalui
    0.92
     accomplished
    0.91
    Activations Density 0.031%

    No Known Activations