© 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. 27898
    Prev
    Next
    INDEX
    Explanations

    followed by a description or definition

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

    The neuron responds most strongly to mentions of historical Christian persecution and early Church figures in medieval religious biographies.

    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
     our
    -1.35
    Дереккөздер
    -1.30
     Sekarang
    -1.26
     lately
    -1.24
     botol
    -1.22
    Външни
    -1.21
     these
    -1.20
     Fitur
    -1.18
     gratific
    -1.18
     bershka
    -1.17
    POSITIVE LOGITS
    🧍
    1.14
    '/',
    1.09
    ofan
    1.04
     animated
    1.02
     after
    1.02
    <strong>
    1.02
     bea
    1.00
     accountId
    1.00
     eff
    0.98
    🧾
    0.98
    Activations Density 0.022%

    No Known Activations