© 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. 66990
    Prev
    Next
    INDEX
    Explanations

    religious affiliation and organizations

    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
     from
    -1.34
     sonunda
    -1.34
     or
    -1.32
    してから
    -1.27
     rijden
    -1.18
     almak
    -1.16
     fiyatı
    -1.16
     bestaan
    -1.14
     verke
    -1.10
     name
    -1.07
    POSITIVE LOGITS
    AKERS
    1.19
     Tienen
    1.17
     {
    1.16
     here
    1.16
     Otras
    1.15
    यह
    1.15
    ֹא
    1.13
    揠
    1.13
    balleur
    1.13
    izability
    1.11
    Activations Density 0.359%

    No Known Activations