© 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. 59408
    Prev
    Next
    INDEX
    Explanations

    biblical figures and concepts

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

    The neuron flags citations of religious (especially Biblical) book names and their accompanying chapter or verse numbers.

    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
    実践
    -1.37
     girar
    -1.25
     caballo
    -1.20
    Öl
    -1.13
     alcalde
    -1.11
    hojas
    -1.09
     deaktivi
    -1.09
    sigue
    -1.07
    オフィス
    -1.07
     novio
    -1.06
    POSITIVE LOGITS
    </h5>
    1.43
    </td>
    1.41
    ffiche
    1.27
    </em>
    1.26
    }}/>
    1.24
    ");
    1.20
    BuildContext
    1.20
    只能
    1.19
    СЯ
    1.18
     alene
    1.17
    Activations Density 0.026%

    No Known Activations