© 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. 32736
    Prev
    Next
    INDEX
    Explanations

    origin and destination

    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
     soumis
    -0.82
     inizi
    -0.72
    CascadeType
    -0.71
    лея
    -0.69
    anyo
    -0.69
    Cause
    -0.69
    daya
    -0.69
     csalá
    -0.69
    Classified
    -0.69
    isters
    -0.68
    POSITIVE LOGITS
     destination
    2.45
     host
    2.14
    destination
    1.92
     originating
    1.87
     home
    1.84
     sending
    1.78
     hosting
    1.70
     receiving
    1.67
     exporting
    1.66
    host
    1.60
    Activations Density 0.071%

    No Known Activations