© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111934
    Prev
    Next
    INDEX
    Explanations

    asteroid city or disaster

    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_40_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
    검
    0.41
     contract
    0.39
     Contract
    0.39
     dark
    0.39
    污
    0.38
     goth
    0.38
    Living
    0.38
    Boxing
    0.37
    Ordering
    0.37
     Gyne
    0.37
    POSITIVE LOGITS
     disaster
    0.83
     Disaster
    0.79
    災害
    0.69
     आपदा
    0.69
     disasters
    0.66
    防災
    0.64
     bencana
    0.61
    灾
    0.57
     panicked
    0.57
     Scientists
    0.56
    Activations Density 0.028%

    No Known Activations