© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2708
    Prev
    Next
    INDEX
    Explanations

    major hurricanes and storm names

    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
     lò
    -0.98
     Dropout
    -0.90
    دست
    -0.85
    DECREF
    -0.82
    olving
    -0.82
     pistols
    -0.81
    クール
    -0.81
     встроен
    -0.81
    ASK
    -0.80
     filós
    -0.80
    POSITIVE LOGITS
     storm
    1.67
     hurricane
    1.63
     Hurricane
    1.40
     forecast
    1.30
    Hurricane
    1.27
     forecasts
    1.23
     weather
    1.18
     meteoro
    1.17
     winds
    1.12
    storm
    1.11
    Activations Density 0.055%

    No Known Activations