© 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. 34-GEMMASCOPE-RES-131K
    7. 98069
    Prev
    Next
    INDEX
    Explanations

    participation in crimes

    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
     might
    -1.36
     if
    -1.23
     people
    -1.23
     any
    -1.22
     possibly
    -1.12
     may
    -1.09
     potentially
    -1.09
     would
    -1.09
     that
    -1.06
     this
    -1.06
    POSITIVE LOGITS
    volvement
    1.33
    particip
    1.25
     orchestr
    1.22
     Partici
    1.20
     participer
    1.20
     partici
    1.20
     légumes
    1.20
     PARTICIP
    1.14
    belong
    1.12
     coloris
    1.11
    Activations Density 0.042%

    No Known Activations