© 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. 10-GEMMASCOPE-RES-131K
    7. 14984
    Prev
    Next
    INDEX
    Explanations

    names of churches and religious places

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

    The main thing this neuron does is detect occurrences of the word “Church” (especially as part of proper names of church buildings or institutions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    写真を撮
    -2.98
    狨
    -2.59
    栳
    -2.52
    鲞
    -2.50
     Achieving
    -2.47
    何故
    -2.45
     freaking
    -2.41
     menac
    -2.41
    ･･
    -2.39
     craz
    -2.34
    POSITIVE LOGITS
    by
    2.97
    }
    2.72
    ла
    2.53
    ㆆ
    2.45
    }$
    2.44
    le
    2.41
    c
    2.39
     hvilket
    2.36
    at
    2.30
     hvilken
    2.28
    Activations Density 0.010%

    No Known Activations