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. 7495
    Prev
    Next
    INDEX
    Explanations

    import BeautifulSoup

    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
    鏟
    0.30
    ጷ
    0.27
    स्परिक
    0.26
     JESUS
    0.26
     sostenibilidad
    0.26
     estándares
    0.25
    त्रेयी
    0.25
     आईडी
    0.25
    剷
    0.25
     історії
    0.24
    POSITIVE LOGITS
    soup
    0.28
    is
    0.27
    bootstrap
    0.26
     disc
    0.25
    dam
    0.24
    Soup
    0.24
    ih
    0.24
    disc
    0.24
    nam
    0.24
    cum
    0.24
    Activations Density 0.001%

    No Known Activations