© 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. 48631
    Prev
    Next
    INDEX
    Explanations

    words starting with lo or lu

    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
    判斷
    -1.44
     parlar
    -1.34
     lèvres
    -1.32
    榀
    -1.30
    vantaged
    -1.28
     consape
    -1.28
     likelihood
    -1.27
     Prevents
    -1.27
    ⁧
    -1.27
     ถ้า
    -1.25
    POSITIVE LOGITS
     credence
    1.30
    LO
    1.27
    ?"
    1.26
    OM
    1.23
    さんも
    1.18
    \
    1.17
     THOSE
    1.17
    虽
    1.15
    ’
    1.15
    </h2>
    1.13
    Activations Density 0.045%

    No Known Activations