© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12787
    Prev
    Next
    INDEX
    Explanations

    asking 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
     matching
    -0.81
    ecker
    -0.78
     densities
    -0.76
     fines
    -0.76
    不但
    -0.75
    によく
    -0.75
    pagnol
    -0.74
     praktischen
    -0.73
    anyard
    -0.73
     Matching
    -0.73
    POSITIVE LOGITS
     shouldn
    1.80
     Shouldn
    1.42
     why
    1.38
    Shouldn
    1.38
     should
    1.38
     debería
    1.21
     Why
    1.10
     ideally
    1.02
     dovrebbe
    1.01
     deberían
    1.01
    Activations Density 0.049%

    No Known Activations