© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28656
    Prev
    Next
    INDEX
    Explanations

    triggering actions or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    有一個
    0.41
    缰
    0.41
    ся
    0.40
    ский
    0.40
    ją
    0.40
     لحاظ
    0.39
    вся
    0.39
     vzděl
    0.39
    ㅕ
    0.39
     odpowied
    0.39
    POSITIVE LOGITS
     launches
    0.55
     émissions
    0.52
     emisiones
    0.50
     initiates
    0.49
     triggers
    0.49
     broadcasts
    0.48
     emotes
    0.48
     debuts
    0.47
     petitions
    0.46
    trigger
    0.46
    Activations Density 0.007%

    No Known Activations