© 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-262K
    7. 71226
    Prev
    Next
    INDEX
    Explanations

    section followed by numbers

    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_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
     మె
    0.39
     Appearance
    0.39
    挈
    0.39
    ưởng
    0.38
     درد
    0.38
    צו
    0.38
     mè
    0.37
     troubles
    0.37
     Pseudo
    0.37
    ో
    0.37
    POSITIVE LOGITS
                 
    0.44
                  
    0.41
    ```
    0.37
    meter
    0.36
    0.36
    omorphisms
    0.35
    ao
    0.35
    generating
    0.35
                
    0.34
    potent
    0.34
    Activations Density 0.002%

    No Known Activations