© 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. 102284
    Prev
    Next
    INDEX
    Explanations

    events of arrival, addition, death, departure

    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
     other
    -1.65
    The
    -1.55
    He
    -1.52
    of
    -1.48
    as
    -1.45
    itados
    -1.41
     They
    -1.40
     There
    -1.40
     نمی
    -1.37
     transacción
    -1.33
    POSITIVE LOGITS
    聍
    1.78
     höl
    1.70
     sonre
    1.60
     siquiera
    1.53
     katk
    1.52
    ໊
    1.52
    einer
    1.48
    izacion
    1.47
    Krank
    1.46
    まさかの
    1.45
    Activations Density 0.079%

    No Known Activations