© 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. 12023
    Prev
    Next
    INDEX
    Explanations

    participant or person involved

    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
    かい
    -0.77
    adar
    -0.75
    Fø
    -0.73
    స
    -0.71
     mpl
    -0.71
     този
    -0.70
     stones
    -0.69
    梗
    -0.69
     autonomic
    -0.69
    adors
    -0.69
    POSITIVE LOGITS
     participant
    1.47
     participants
    1.38
     Participant
    1.30
     Participants
    1.25
    Participants
    1.20
    Participant
    1.20
    participant
    1.20
    participants
    1.20
     participantes
    0.95
     Teilnehmer
    0.85
    Activations Density 0.013%

    No Known Activations