© 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. 34-GEMMASCOPE-RES-131K
    7. 90731
    Prev
    Next
    INDEX
    Explanations

    criticism and critics

    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
     impone
    -1.04
     ilha
    -0.98
     investimento
    -0.97
     boasting
    -0.96
    culi
    -0.94
     Between
    -0.94
     Diskussion
    -0.93
     trasm
    -0.93
    cilis
    -0.93
     Clearly
    -0.93
    POSITIVE LOGITS
    isim
    1.14
     constructive
    1.13
    ising
    1.09
    icism
    1.09
    ical
    1.02
    ByteString
    0.98
    tics
    0.97
    ammlung
    0.95
     levelled
    0.94
     lakini
    0.93
    Activations Density 0.014%

    No Known Activations