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. 578
    Prev
    Next
    INDEX
    Explanations

    entity and its location

    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
    इसका
    0.41
    রূপে
    0.37
    📀
    0.36
     त्यात
    0.35
     consigo
    0.34
    sadpoetry
    0.33
    脩
    0.33
     περιο
    0.33
    ពេលវេល
    0.33
    chaoxing
    0.33
    POSITIVE LOGITS
     tại
    2.02
     at
    1.72
    Tại
    1.47
     chez
    1.45
     presso
    1.41
     Tại
    1.41
     لدى
    1.23
     atthe
    1.23
     ở
    1.15
    ຢູ່
    1.13
    Activations Density 0.017%

    No Known Activations