© 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. 13708
    Prev
    Next
    INDEX
    Explanations

    Bohemian Rhapsody and We Will Rock You

    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
     Mittag
    0.40
    DataDiv
    0.38
    Ὑ
    0.38
    atonic
    0.36
    ツイ
    0.36
     Holton
    0.36
     Armour
    0.35
    态
    0.35
    タミン
    0.35
     Pickering
    0.35
    POSITIVE LOGITS
     ViewController
    0.70
    ViewController
    0.65
    addView
    0.62
    Interceptor
    0.54
     WebView
    0.51
    setView
    0.50
    EnableWeb
    0.50
     viewController
    0.50
     ModelAndView
    0.48
    WebView
    0.47
    Activations Density 0.003%

    No Known Activations