© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82355
    Prev
    Next
    INDEX
    Explanations

    tropical cyclones and storms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mountains
    -0.85
     perch
    -0.79
    ues
    -0.78
    raktion
    -0.77
     joh
    -0.77
    Vibr
    -0.77
    äť
    -0.75
     ढ
    -0.74
    蝙蝠
    -0.74
    السكان
    -0.73
    POSITIVE LOGITS
     storm
    2.22
     storms
    2.13
     hurricane
    2.09
     hurricanes
    1.98
     typhoon
    1.69
     cyclone
    1.59
    storm
    1.55
     tornado
    1.48
    storms
    1.40
     Hurricanes
    1.39
    Activations Density 0.032%

    No Known Activations