© 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. 73828
    Prev
    Next
    INDEX
    Explanations

    telling how to explain

    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
     envelop
    -1.50
    ？！”
    -1.48
     одежду
    -1.44
    ⊓
    -1.38
    d
    -1.38
     Klasse
    -1.36
    八幡
    -1.35
     neuf
    -1.34
    foreignKey
    -1.32
    Созда
    -1.32
    POSITIVE LOGITS
    知り
    1.88
     oczywiście
    1.84
     tradisi
    1.84
    ”:
    1.70
     Furcht
    1.63
    桕
    1.62
     gesagt
    1.62
    ’:
    1.61
    必要的
    1.59
    昔から
    1.59
    Activations Density 0.014%

    No Known Activations