© 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. 22-GEMMASCOPE-RES-131K
    7. 130280
    Prev
    Next
    INDEX
    Explanations

    should

    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
    だけではなく
    -1.38
     entièrement
    -1.26
    すっ
    -1.23
     conductores
    -1.22
    だけでなく
    -1.18
    向けの
    -1.17
     realmente
    -1.16
    えっ
    -1.13
     camiones
    -1.13
    Bitcoin
    -1.13
    POSITIVE LOGITS
     when
    1.85
     because
    1.61
     should
    1.31
     people
    1.30
     When
    1.30
    when
    1.28
     those
    1.28
     while
    1.24
     does
    1.20
     started
    1.20
    Activations Density 0.020%

    No Known Activations