© 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. 66719
    Prev
    Next
    INDEX
    Explanations

    user update on projects

    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
     these
    -1.72
    these
    -1.66
     theſe
    -1.61
     each
    -1.56
    そうに
    -1.45
     sooo
    -1.40
     THESE
    -1.38
     These
    -1.38
     tellement
    -1.38
    hanno
    -1.38
    POSITIVE LOGITS
     after
    1.90
     first
    1.58
    にしました
    1.35
    ⬯
    1.35
     without
    1.35
    我们在
    1.34
     przód
    1.34
    二日
    1.33
    やった
    1.32
     during
    1.31
    Activations Density 0.083%

    No Known Activations