© 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-262K
    7. 113448
    Prev
    Next
    INDEX
    Explanations

    database, volunteered, research, policies

    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
    overflow
    0.50
    小
    0.50
    +
    0.50
     scratched
    0.47
     sprouts
    0.45
     grafted
    0.44
     flashes
    0.44
     crystals
    0.43
     soda
    0.43
     perforated
    0.43
    POSITIVE LOGITS
     Junto
    0.55
     Democracy
    0.54
     सशक्त
    0.52
     democracy
    0.52
     демокра
    0.48
    🤝
    0.48
     Policies
    0.47
     अफसर
    0.47
     Representations
    0.47
     demokrasi
    0.47
    Activations Density 0.002%

    No Known Activations