© 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. 16-GEMMASCOPE-2-RES-262K
    7. 19899
    Prev
    Next
    INDEX
    Explanations

    provisional diagnosis, dorsal fin, free skate

    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_16_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
     incentiv
    0.59
    entu
    0.56
    inicio
    0.56
    nove
    0.54
    一個
    0.52
     linguistics
    0.52
    𝗺
    0.52
     ciep
    0.52
    mousemove
    0.51
     दोघा
    0.51
    POSITIVE LOGITS
     приложение
    0.59
    0.56
    Y
    0.54
                    
    0.53
    J
    0.53
     varsa
    0.53
    ية
    0.52
    اعة
    0.50
                              
    0.50
    N
    0.50
    Activations Density 0.000%

    No Known Activations