© 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. 100689
    Prev
    Next
    INDEX
    Explanations

    AP Photo citations

    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
    臯
    -2.13
    SaveChangesAsync
    -1.84
    ﺲ
    -1.81
    ܆
    -1.78
    鍆
    -1.78
     pauv
    -1.77
    珢
    -1.74
    ፧
    -1.74
    傒
    -1.73
    輅
    -1.71
    POSITIVE LOGITS
     of
    2.36
     for
    2.02
     by
    2.00
     even
    1.88
     "";
    1.73
     or
    1.73
     with
    1.70
    »،
    1.65
     without
    1.65
     up
    1.63
    Activations Density 0.001%

    No Known Activations