© 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. 11623
    Prev
    Next
    INDEX
    Explanations

    hay for animals

    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
    t
    1.05
    ↵
    0.98
    /
    0.80
    \
    0.79
                
    0.75
    z
    0.73
     V
    0.72
        
    0.69
     computation
    0.69
    ó
    0.69
    POSITIVE LOGITS
    ﻥ
    0.90
    ;</
    0.80
     入っ
    0.76
    )$:
    0.74
    あらゆる
    0.73
    ﺭ
    0.73
    ⅽ
    0.73
    cliente
    0.71
    必要な
    0.71
     ιδια
    0.71
    Activations Density 0.000%

    No Known Activations