© 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-65K
    7. 53057
    Prev
    Next
    INDEX
    Explanations

    qualities of options

    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_65k_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
    t
    0.55
     اسمها
    0.49
    bundles
    0.47
     immediacy
    0.46
     imperatives
    0.46
     መጠ
    0.46
    Cla
    0.45
     equations
    0.45
    4
    0.44
    aboration
    0.44
    POSITIVE LOGITS
     fazer
    0.54
    ถ้า
    0.52
     pourcentage
    0.52
    的な
    0.50
    ຫນ
    0.50
    πο
    0.48
    ρή
    0.48
     fazia
    0.48
     comisión
    0.47
     choisi
    0.47
    Activations Density 0.012%

    No Known Activations