Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8724
    Prev
    Next
    INDEX
    Explanations

    Fukushima nuclear disaster

    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
     apartado
    -0.81
     berubah
    -0.80
     نار
    -0.73
    hashCode
    -0.72
    calle
    -0.72
     tinder
    -0.71
    maksud
    -0.71
    essore
    -0.71
    unaga
    -0.69
     werfen
    -0.68
    POSITIVE LOGITS
     Fukushima
    1.79
     nuclear
    1.40
     radiation
    1.38
     reactor
    1.30
    Fuk
    1.22
    fuk
    1.16
    radiation
    1.13
    Nuclear
    1.12
    nuclear
    1.09
     meltdown
    1.09
    Activations Density 0.025%

    No Known Activations