© 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. 34-GEMMASCOPE-RES-131K
    7. 58149
    Prev
    Next
    INDEX
    Explanations

    state of being ready to

    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_34/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
    ことになる
    -0.84
     postulated
    -0.81
     rất
    -0.80
     anzu
    -0.80
     dezelfde
    -0.79
     suffisamment
    -0.79
     initialized
    -0.78
    .
    -0.78
     was
    -0.78
    dihydro
    -0.78
    POSITIVE LOGITS
     suddenly
    1.26
     accurately
    1.18
     somehow
    1.16
    suddenly
    1.16
     actively
    1.13
     simultaneously
    1.12
     calmly
    1.11
     efficiently
    1.10
     faithfully
    1.10
     profitably
    1.09
    Activations Density 0.101%

    No Known Activations