© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15787
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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_40_width_262k_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
    ．
    0.41
     жив
    0.40
    说过
    0.37
    
    0.36
    LookAnd
    0.35
     engage
    0.35
    、“
    0.35
    Proceedings
    0.34
    
    0.34
    versus
    0.34
    POSITIVE LOGITS
    វិ
    0.40
     gustaría
    0.38
    EUI
    0.38
    homotopic
    0.38
    gmail
    0.37
     προβ
    0.37
     weiteres
    0.36
     homotopic
    0.35
     ペンダント
    0.35
     खरेदी
    0.35
    Activations Density 0.002%

    No Known Activations