Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 15267
    Prev
    Next
    INDEX
    Explanations

    fan performance and status

    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
    Forg
    0.42
    шили
    0.40
     уголов
    0.40
    生理
    0.39
     धोखाध
    0.38
    琐
    0.38
     sostuvo
    0.38
     くれ
    0.38
    妊娠
    0.38
     краё
    0.37
    POSITIVE LOGITS
     fan
    1.63
     fans
    1.45
    fan
    1.31
     Fan
    1.30
     Fans
    1.28
    Fan
    1.27
     ventilation
    1.23
    fans
    1.21
     팬
    1.21
     pump
    1.20
    Activations Density 0.021%

    No Known Activations