© 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. 39801
    Prev
    Next
    INDEX
    Explanations

    years and entities followed by events

    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
     jaren
    -1.48
    屃
    -1.42
    woners
    -1.40
    СТВО
    -1.39
     inond
    -1.38
     nettoyer
    -1.36
     réparer
    -1.35
    pherds
    -1.30
     terminer
    -1.30
    힣
    -1.28
    POSITIVE LOGITS
     about
    1.61
     which
    1.48
     so
    1.47
    ↵
    1.24
     около
    1.20
    While
    1.16
    زيل
    1.10
    Through
    1.09
     "
    1.08
     They
    1.07
    Activations Density 0.297%

    No Known Activations