© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2876
    Prev
    Next
    INDEX
    Explanations

    weather and storms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    istor
    1.22
     Oste
    1.06
    }}\|
    1.03
    棄
    0.98
     genetics
    0.96
    elter
    0.96
     oligonucle
    0.95
    ooker
    0.94
     euthanasia
    0.93
     genome
    0.92
    POSITIVE LOGITS
     devils
    1.93
    🌩
    1.75
     fuerte
    1.75
     سته
    1.71
     putern
    1.71
    storms
    1.70
    thunder
    1.69
     thunderstorms
    1.68
    Nimbus
    1.66
     landfall
    1.65
    Activations Density 0.113%

    No Known Activations