© 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. 1746
    Prev
    Next
    INDEX
    Explanations

    as, in the capacity of, role

    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
    你怎么
    -0.81
     helps
    -0.79
     привести
    -0.75
     basically
    -0.73
    isic
    -0.71
    ToRefresh
    -0.70
     Creating
    -0.69
     Basically
    -0.66
     bringing
    -0.66
     provide
    -0.66
    POSITIVE LOGITS
    作为
    1.34
    作為
    1.24
    として
    1.17
     functioning
    1.09
     качестве
    1.07
    作为一个
    1.04
    身为
    1.04
     emerged
    1.02
     jako
    1.00
     функциони
    1.00
    Activations Density 0.147%

    No Known Activations