© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70429
    Prev
    Next
    INDEX
    Explanations

    evangelical Christian faith

    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
    '
    -2.83
    骉
    -2.47
    several
    -2.39
     anderen
    -2.30
     elegantly
    -2.27
    嘖
    -2.23
     sooo
    -2.23
     amazingly
    -2.22
     основной
    -2.17
     fabulous
    -2.16
    POSITIVE LOGITS
    there
    2.73
     There
    2.64
    After
    2.44
    ቍ
    2.25
    There
    2.22
    ruvate
    2.19
     time
    2.16
    When
    2.09
    One
    2.09
     for
    2.09
    Activations Density 0.002%

    No Known Activations