Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16151
    Prev
    Next
    INDEX
    Explanations

    code structure and punctuation

    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
     étroites
    0.48
    များနှင့်
    0.44
    .'),
    0.43
     നിങ്ങളുടെ
    0.43
     bactéries
    0.43
    㥆
    0.43
     capables
    0.42
    城市的
    0.42
    .«
    0.42
     लोका
    0.42
    POSITIVE LOGITS
     )
    0.56
    j
    0.47
     see
    0.46
    ↵↵
    0.45
      
    0.45
    see
    0.44
    this
    0.43
     Return
    0.43
     ]
    0.42
     NOTE
    0.41
    Activations Density 0.155%

    No Known Activations