© 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. 28385
    Prev
    Next
    INDEX
    Explanations

    code markers

    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
     músculo
    -1.10
     każ
    -1.09
    Again
    -1.06
     they
    -1.04
    totalCount
    -1.04
     Jugendliche
    -1.00
    hecimento
    -0.99
     wacht
    -0.98
    apnews
    -0.98
     капю
    -0.97
    POSITIVE LOGITS
    作战
    1.05
     recollection
    0.96
     recomand
    0.95
     위한
    0.94
     trac
    0.93
    extra
    0.92
    Legenda
    0.92
    Oblig
    0.92
    を用
    0.92
    结语
    0.91
    Activations Density 0.004%

    No Known Activations