© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93880
    Prev
    Next
    INDEX
    Explanations

    cyclone intensity estimation

    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
     едва
    -0.77
     costo
    -0.73
     Jane
    -0.71
     Harald
    -0.70
    selaer
    -0.70
     Théâtre
    -0.68
     abundances
    -0.68
    看待
    -0.68
    škas
    -0.68
    };
    -0.65
    POSITIVE LOGITS
     MCS
    0.87
     day
    0.84
     electrification
    0.82
    MatInputModule
    0.81
    Day
    0.80
    ekw
    0.79
    暧
    0.79
    日目
    0.77
    eningrad
    0.77
     寝
    0.77
    Activations Density 0.018%

    No Known Activations