© 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. 22-GEMMASCOPE-RES-131K
    7. 39097
    Prev
    Next
    INDEX
    Explanations

    understand why

    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_22/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
     vostre
    -1.05
     エコ
    -1.05
     JAXBElement
    -1.00
    じゃなくて
    -0.96
     benzina
    -0.96
     кое
    -0.96
    はかなり
    -0.96
     citazioni
    -0.94
     pagine
    -0.94
    کہ
    -0.93
    POSITIVE LOGITS
     why
    3.42
     Why
    2.50
    Why
    2.34
     how
    2.30
    why
    2.11
    为什么
    2.05
    なぜ
    1.95
     WHY
    1.91
     pourquoi
    1.84
     waarom
    1.84
    Activations Density 0.049%

    No Known Activations