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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9999
    Prev
    Next
    INDEX
    Explanations

    natural disaster preparedness

    np_acts-logits-general · gemini-2.5-flash-lite

    natural disasters

    np_acts-logits-general · gemini-2.5-flash-lite

    disaster

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    രിച്ചത്
    0.40
    dagger
    0.40
    抺
    0.39
    甄
    0.39
    廝
    0.39
    激烈
    0.38
     dagger
    0.38
     minY
    0.38
    搔
    0.38
     함
    0.37
    POSITIVE LOGITS
     disaster
    2.11
     Disaster
    2.06
    災害
    1.91
     disasters
    1.90
     आपदा
    1.80
    灾
    1.76
     bencana
    1.69
    防災
    1.61
     FEMA
    1.57
    災
    1.56
    Activations Density 0.199%

    No Known Activations