© 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. 56294
    Prev
    Next
    INDEX
    Explanations

    Reduced microbial exposure, confused potato

    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
    CISE
    0.46
    ibold
    0.43
    <0xD9>
    0.42
    بە
    0.42
    hent
    0.42
    ਦ
    0.41
    ἐ
    0.41
     Ə
    0.41
    لە
    0.41
    ipio
    0.41
    POSITIVE LOGITS
     Jeans
    0.53
     Leafs
    0.50
     Truss
    0.48
     Kab
    0.48
     Eagles
    0.47
     海外
    0.46
     Anatomy
    0.45
     Braves
    0.45
    ภู
    0.45
     Cloth
    0.45
    Activations Density 0.015%

    No Known Activations