© 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. 68831
    Prev
    Next
    INDEX
    Explanations

    happens only once

    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
    0
    -1.04
     Fotografía
    -1.00
     hadn
    -0.94
    きち
    -0.92
    PID
    -0.91
     varietà
    -0.90
    えません
    -0.90
    يمة
    -0.89
     छोट
    -0.89
     hitherto
    -0.89
    POSITIVE LOGITS
     then
    1.20
    Then
    1.02
    で
    1.00
    袈
    0.98
     irreversible
    0.96
     before
    0.96
     dejo
    0.96
    ."
    0.96
    r
    0.94
    ὲ
    0.93
    Activations Density 0.021%

    No Known Activations