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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 48
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
    表达式
    0.35
     இரண்டு
    0.33
     vijf
    0.33
    :"
    0.32
     ttl
    0.32
     "//
    0.32
     foo
    0.32
    ])
    0.31
     शेट्टी
    0.31
     `"
    0.31
    POSITIVE LOGITS
     monitoring
    0.45
    when
    0.45
    regarding
    0.45
     when
    0.44
     oversight
    0.44
     whilst
    0.42
     minimise
    0.42
     minimising
    0.42
     regarding
    0.41
     overseeing
    0.40
    Activations Density 0.000%

    No Known Activations