© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32506
    Prev
    Next
    INDEX
    Explanations

    time when or where

    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
     quello
    -0.89
    artment
    -0.89
    who
    -0.88
    เพราะ
    -0.87
    ност
    -0.87
    ترنت
    -0.85
     Who
    -0.84
    ophiles
    -0.84
    因为
    -0.84
    并将
    -0.83
    POSITIVE LOGITS
     that
    1.98
     of
    1.58
     when
    1.37
     where
    1.34
     whereby
    1.18
     که
    1.15
     wherein
    1.11
     kdy
    1.09
     hvor
    1.07
     dimana
    1.07
    Activations Density 0.038%

    No Known Activations