© 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. 128010
    Prev
    Next
    INDEX
    Explanations

    evangelical faith and Christian contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    of
    -2.63
    9
    -2.61
    1
    -2.58
    8
    -2.44
    $,
    -2.44
    7
    -2.41
    a
    -2.36
    ization
    -2.36
     OF
    -2.34
    6
    -2.33
    POSITIVE LOGITS
    栳
    2.92
    ’
    2.83
    薆
    2.64
    鬭
    2.56
    ’，
    2.56
     cardin
    2.41
    鷙
    2.41
    Ꮟ
    2.39
    zelfde
    2.38
    鱟
    2.38
    Activations Density 0.064%

    No Known Activations