© 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. 116868
    Prev
    Next
    INDEX
    Explanations

    weather and locations

    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
     $.
    -0.84
    dictions
    -0.80
    かなりの
    -0.78
     pubblic
    -0.76
     hidratante
    -0.76
     estratégico
    -0.75
    rego
    -0.73
    جابة
    -0.73
     gemens
    -0.73
     conductas
    -0.72
    POSITIVE LOGITS
    alış
    0.85
     Dumnezeu
    0.83
    료
    0.81
     frisk
    0.79
    🏟
    0.78
    inka
    0.76
    Estadio
    0.76
     Där
    0.75
     diplôme
    0.75
    ReusableCell
    0.75
    Activations Density 0.004%

    No Known Activations