© 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. 115505
    Prev
    Next
    INDEX
    Explanations

    Portsmouth and naval subjects

    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
     quel
    -0.76
    oval
    -0.76
    enie
    -0.75
    <0xED>
    -0.73
    UDES
    -0.71
     Nevis
    -0.71
    beh
    -0.71
    IAR
    -0.71
    produces
    -0.69
    ändler
    -0.69
    POSITIVE LOGITS
     Portsmouth
    2.03
    Ports
    1.40
     Pompey
    1.21
    PORTS
    0.98
     Shawnee
    0.89
     POR
    0.82
     Heinemann
    0.79
     Bremer
    0.76
     Naval
    0.74
    mouth
    0.73
    Activations Density 0.032%

    No Known Activations