© 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. 85350
    Prev
    Next
    INDEX
    Explanations

    fallacies, folly, fallibility

    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
    絰
    -2.72
    飧
    -2.48
    ︕
    -2.47
     ſont
    -2.45
    YNAMIC
    -2.44
     oxu
    -2.41
    ،
    -2.36
    瞟
    -2.34
    窳
    -2.28
    ⽤
    -2.22
    POSITIVE LOGITS
    7
    3.11
    1
    2.55
    2
    2.52
    4
    2.52
    3
    2.50
    8
    2.45
    Y
    2.42
    also
    2.39
    5
    2.34
     
    2.31
    Activations Density 0.002%

    No Known Activations