© 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. 1558
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    一个
    0.21
    Lazy
    0.19
    sbParams
    0.19
    ộng
    0.19
    ৭০
    0.19
     Siamese
    0.19
    畬
    0.18
    Javascript
    0.18
    软
    0.18
    Variable
    0.17
    POSITIVE LOGITS
     were
    0.24
     waren
    0.23
     fueron
    0.22
     representante
    0.21
     hatta
    0.20
     districts
    0.19
     funcionarios
    0.19
     quanto
    0.19
     industriale
    0.19
     করিয়াছিলেন
    0.19
    Activations Density 0.028%

    No Known Activations