© 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. 28038
    Prev
    Next
    INDEX
    Explanations

    common phrases and follow-ups

    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
     approu
    0.47
    en
    0.45
    re
    0.44
    et
    0.43
     \
    0.42
    kaw
    0.42
    iques
    0.42
     apprentices
    0.42
    F
    0.41
     equival
    0.41
    POSITIVE LOGITS
    쌌
    0.45
     были
    0.45
    が通販
    0.44
    
    0.44
     করেছিলেন
    0.43
     краї
    0.42
    ᠩ
    0.42
     смогли
    0.41
    鉈
    0.41
     блока
    0.40
    Activations Density 0.017%

    No Known Activations