© 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. 13477
    Prev
    Next
    INDEX
    Explanations

    explaining specific terms

    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
     I
    0.42
    ↵
    0.41
            
    0.38
        
    0.37
    ical
    0.37
     and
    0.37
    ud
    0.37
    T
    0.37
    <b>
    0.36
          
    0.36
    POSITIVE LOGITS
     vasodil
    0.32
    وڑا
    0.32
    плення
    0.32
     translocation
    0.31
     secretions
    0.31
     apportionment
    0.31
     bioavailability
    0.30
     crystallinity
    0.30
     drunkenness
    0.30
     spasms
    0.30
    Activations Density 0.038%

    No Known Activations