© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129308
    Prev
    Next
    INDEX
    Explanations

    end of phrases followed by common words

    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
    ınız
    -1.57
    ministerium
    -1.42
     atractiva
    -1.41
    lihatan
    -1.41
     jetzt
    -1.38
    Descriere
    -1.35
     illetve
    -1.30
    ೢ
    -1.28
    agosto
    -1.28
     SOMETHING
    -1.27
    POSITIVE LOGITS
     that
    2.11
     also
    1.98
     their
    1.71
     usually
    1.58
     often
    1.54
     for
    1.48
     want
    1.47
     which
    1.44
     another
    1.43
     this
    1.40
    Activations Density 0.074%

    No Known Activations