© 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. 22-GEMMASCOPE-RES-131K
    7. 34560
    Prev
    Next
    INDEX
    Explanations

    currying, trekking, neurokinin, economic burden, Sarah Carey

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

    This neuron detects explicit references to trusting or depending on God (e.g., “trust,” “Lord,” “God,” “promised”).

    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
     intitulé
    -1.46
    がありますが
    -1.43
     πρ
    -1.42
    你们的
    -1.40
     våra
    -1.39
     různ
    -1.35
     Vereinbarung
    -1.32
     fotográfica
    -1.30
     kilku
    -1.29
    真剣
    -1.29
    POSITIVE LOGITS
     was
    1.99
     his
    1.90
     had
    1.84
     himself
    1.64
     knew
    1.56
     hadn
    1.47
     he
    1.46
     their
    1.41
     him
    1.35
    "}";
    1.34
    Activations Density 0.010%

    No Known Activations