© 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. 70929
    Prev
    Next
    INDEX
    Explanations

    biblical teachings

    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
     with
    -1.79
    tling
    -1.69
     For
    -1.61
    🢒
    -1.56
     यदि
    -1.56
     They
    -1.53
    皛
    -1.52
     These
    -1.52
     for
    -1.48
     in
    -1.42
    POSITIVE LOGITS
    ”،
    1.66
     your
    1.59
    찮
    1.53
    u
    1.52
    姈
    1.45
     セン
    1.41
    ふう
    1.41
     adecuadamente
    1.40
     最終
    1.40
    何度も
    1.40
    Activations Density 0.010%

    No Known Activations