© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57564
    Prev
    Next
    INDEX
    Explanations

    conference attendees and speakers

    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
    complished
    -1.11
     kaynağından
    -1.00
    ğan
    -0.93
    matchCondition
    -0.92
    dań
    -0.90
    zések
    -0.90
    quirer
    -0.89
    搡
    -0.89
    ́s
    -0.89
    writes
    -0.89
    POSITIVE LOGITS
     attendees
    3.16
     speakers
    2.70
     audience
    2.61
     speaker
    2.50
     attendee
    2.41
     presenters
    2.25
     panelists
    2.11
     keynote
    2.06
     presentations
    2.03
     session
    2.02
    Activations Density 0.057%

    No Known Activations