Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 2192
    Prev
    Next
    INDEX
    Explanations

    actions performed with intensity

    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
    <0xE2>
    0.17
                            
    0.16
    <0xE3>
    0.16
                     
    0.16
     
    0.16
             
    0.14
     ∂
    0.14
                 
    0.14
     sighed
    0.14
            
    0.14
    POSITIVE LOGITS
     furiously
    0.28
     extensively
    0.25
     freely
    0.24
     competitively
    0.23
     vigorously
    0.22
     incessantly
    0.22
     uncontroll
    0.21
     peacefully
    0.21
     autonomously
    0.20
     recklessly
    0.20
    Activations Density 0.118%

    No Known Activations