© 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. 22-GEMMASCOPE-RES-131K
    7. 33203
    Prev
    Next
    INDEX
    Explanations

    Christian theological texts

    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_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
    Fär
    -1.39
     although
    -1.31
     during
    -1.29
     ristor
    -1.29
     many
    -1.26
    زاده
    -1.20
    সূত্র
    -1.19
    During
    -1.16
     young
    -1.15
    ★☆
    -1.15
    POSITIVE LOGITS
    ׁ
    1.38
    yors
    1.24
     aesthetics
    1.22
    ১
    1.22
    الإنجليزية
    1.20
    Matt
    1.19
    instagram
    1.16
    、、
    1.16
    ⠀⠀
    1.16
    匮
    1.14
    Activations Density 0.018%

    No Known Activations