© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9838
    Prev
    Next
    INDEX
    Explanations

    penalties, fines, and consequences

    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
     l
    0.61
     this
    0.55
     t
    0.52
     many
    0.51
     has
    0.49
     Many
    0.49
     muss
    0.48
     Cochrane
    0.48
     m
    0.48
    elm
    0.47
    POSITIVE LOGITS
     ставкалары
    0.45
     incentivize
    0.45
     levied
    0.43
     punish
    0.43
     deportes
    0.42
    ꒷
    0.42
    惩
    0.42
    鍰
    0.42
     unjustly
    0.41
     يتعلق
    0.41
    Activations Density 0.096%

    No Known Activations