© 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-16K
    7. 423
    Prev
    Next
    INDEX
    Explanations

    don't something

    np_acts-logits-general · gemini-2.5-flash-lite

    instances of in-word punctuation, especially apostrophes in contractions/possessives and hyphens in compound terms.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_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
     airfoil
    0.19
    }$;
    0.17
     }$
    0.17
                              
    0.17
    '}
    0.16
                 
    0.16
                                   
    0.16
    }$.
    0.16
                    
    0.16
                             
    0.16
    POSITIVE LOGITS
    ChangeEvent
    0.13
    валися
    0.12
    ጀመሪያ
    0.12
    粈
    0.12
    жи
    0.12
    рано
    0.12
    Touched
    0.12
    лося
    0.11
    ለያዩ
    0.11
    પણે
    0.11
    Activations Density 7.420%

    No Known Activations