© 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. 86249
    Prev
    Next
    INDEX
    Explanations

    code documentation keywords

    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
    をつけ
    -1.72
     gän
    -1.66
    媄
    -1.54
     besseren
    -1.51
     černá
    -1.44
     菇
    -1.43
    耷
    -1.41
     يقول
    -1.41
     sicheren
    -1.36
     wesentlichen
    -1.35
    POSITIVE LOGITS
     have
    1.79
    ｅ
    1.59
     has
    1.56
    "
    1.53
     at
    1.52
    1.51
     którzy
    1.43
    📞
    1.43
    　
    1.43
    \
    1.42
    Activations Density 0.025%

    No Known Activations