© 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. 31-GEMMASCOPE-2-RES-65K
    7. 56264
    Prev
    Next
    INDEX
    Explanations

    exercise, api, food, location, action

    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_65k_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
    וד
    0.61
    при
    0.60
    си
    0.60
    ני
    0.60
    ЕР
    0.59
    Altri
    0.59
    ק
    0.59
    לי
    0.59
    КА
    0.59
    ਤੀ
    0.59
    POSITIVE LOGITS
     cells
    0.44
     h
    0.41
     (
    0.41
     y
    0.39
     _
    0.39
     City
    0.39
     securities
    0.39
      
    0.38
     self
    0.38
     whey
    0.38
    Activations Density 0.247%

    No Known Activations