© 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. 67139
    Prev
    Next
    INDEX
    Explanations

    wish for past or hypothetical 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
    probably
    -1.48
     två
    -1.46
    likely
    -1.40
    很多
    -1.38
    を紹介します
    -1.37
    both
    -1.36
     exakt
    -1.33
     renom
    -1.30
    进口
    -1.30
     fournisseur
    -1.29
    POSITIVE LOGITS
     it
    2.33
     this
    2.05
     all
    1.80
     even
    1.78
     at
    1.77
     that
    1.77
     so
    1.76
     more
    1.62
     which
    1.58
     just
    1.52
    Activations Density 0.013%

    No Known Activations