© 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. 16-GEMMASCOPE-2-RES-262K
    7. 11399
    Prev
    Next
    INDEX
    Explanations

    exhaust gases and airflow

    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_16_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
     \
    0.70
    (\
    0.70
     s
    0.65
     d
    0.61
    \
    0.60
    ر
    0.56
     i
    0.56
     de
    0.55
     il
    0.54
    از
    0.53
    POSITIVE LOGITS
     exhaust
    0.65
    𝘔
    0.60
    bpy
    0.59
    ODY
    0.58
     tablespoons
    0.58
    OPHY
    0.57
     airflow
    0.56
    sort
    0.53
     tonnes
    0.52
    speople
    0.52
    Activations Density 0.004%

    No Known Activations