© 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. 71580
    Prev
    Next
    INDEX
    Explanations

    highway construction and maintenance

    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
    ="@+
    -1.23
    jmniej
    -1.14
    REN
    -1.11
    apeno
    -1.09
    Задание
    -1.09
    Monthly
    -1.08
    istung
    -1.05
     Inſ
    -1.05
    styleable
    -1.04
    暧
    -1.04
    POSITIVE LOGITS
     and
    1.19
    litude
    1.19
    м
    1.16
    쉼
    1.16
    Награ
    1.15
     novin
    1.15
    ϖ
    1.10
     if
    1.09
         
    1.07
     stanov
    1.06
    Activations Density 0.081%

    No Known Activations