© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19889
    Prev
    Next
    INDEX
    Explanations

    addresses and committees

    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_31_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
     deja
    0.41
    çay
    0.41
     crea
    0.41
     primordial
    0.41
    ➰
    0.40
     व्हायरल
    0.39
     transforma
    0.39
     solvable
    0.39
     subjug
    0.39
     kaleidoscopic
    0.38
    POSITIVE LOGITS
     Address
    0.88
    Address
    0.83
     address
    0.80
    地址
    0.75
    address
    0.73
     地址
    0.69
     ঠিকানা
    0.65
     адресу
    0.61
     адрес
    0.61
    〒
    0.59
    Activations Density 0.029%

    No Known Activations