© 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. 7792
    Prev
    Next
    INDEX
    Explanations

    slide 2:

    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
    Jer
    0.43
     
    0.39
    felder
    0.39
    see
    0.38
    M
    0.37
    J
    0.37
    rie
    0.37
     рабо
    0.36
    
    0.36
    DI
    0.36
    POSITIVE LOGITS
     impediment
    0.43
     Imped
    0.43
     âng
    0.41
     đôi
    0.41
     magnes
    0.41
    டப்பட்டது
    0.41
    顧客
    0.41
     cityscape
    0.40
     WeChat
    0.40
     benefícios
    0.40
    Activations Density 0.008%

    No Known Activations