© 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. 22-GEMMASCOPE-RES-131K
    7. 65656
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     alcune
    -1.04
     différentes
    -1.02
     znovu
    -1.01
    tats
    -0.99
     alcuni
    -0.98
    athed
    -0.98
     beeld
    -0.97
    levis
    -0.94
    heyd
    -0.94
    ejo
    -0.94
    POSITIVE LOGITS
     despite
    1.02
     strangely
    0.97
     epitom
    0.96
     maxY
    0.96
     touted
    0.96
     demonstrates
    0.95
    ჭ
    0.95
     oddly
    0.94
    ⼩
    0.93
     puts
    0.93
    Activations Density 0.001%

    No Known Activations