© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2640
    Prev
    Next
    INDEX
    Explanations

    attendees and participants

    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_17_width_16k_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
     exploits
    1.01
     exploit
    0.91
     billions
    0.88
     millions
    0.87
    explo
    0.86
     ধ্বংস
    0.82
     bearish
    0.81
    궤
    0.80
     exploited
    0.79
     exploiting
    0.79
    POSITIVE LOGITS
     Attendees
    2.04
     attendee
    2.03
    Participants
    1.97
     attendees
    1.97
    Attendee
    1.97
     Participants
    1.93
    Attendees
    1.93
    Participant
    1.87
     participants
    1.85
    Participation
    1.84
    Activations Density 0.158%

    No Known Activations