© 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. 40-GEMMASCOPE-2-RES-262K
    7. 734
    Prev
    Next
    INDEX
    Explanations

    fans 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_40_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
    Tank
    0.44
    ვილი
    0.44
    狧
    0.43
    谑
    0.43
    Alberta
    0.42
    ębior
    0.42
    akkhati
    0.42
    oscale
    0.41
    栓
    0.41
    坦克
    0.40
    POSITIVE LOGITS
     fan
    0.93
     Fan
    0.91
     fans
    0.90
    Fan
    0.82
     Fans
    0.79
    扇
    0.76
    fan
    0.74
     airflow
    0.73
    Fans
    0.73
     팬
    0.73
    Activations Density 0.005%

    No Known Activations