© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2954
    Prev
    Next
    INDEX
    Explanations

    events and parties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebKit
    0.75
     kubectl
    0.74
    benzoic
    0.70
    奀
    0.66
     diodes
    0.65
     Calibri
    0.65
    rayed
    0.64
     qubits
    0.64
    骛
    0.64
    linalg
    0.64
    POSITIVE LOGITS
     gatherings
    2.67
     party
    2.60
     parties
    2.60
    イベント
    2.56
     events
    2.53
     event
    2.46
     weddings
    2.42
     eventos
    2.41
     мероприятия
    2.32
     Events
    2.31
    Activations Density 0.501%

    No Known Activations