© 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. 83140
    Prev
    Next
    INDEX
    Explanations

    ship followed by related terms

    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
     щоб
    -0.85
     Evento
    -0.84
    にした
    -0.81
    fortunately
    -0.81
     maquina
    -0.79
     obicei
    -0.79
    支払い
    -0.78
    Послед
    -0.76
     Eventos
    -0.76
    cepatan
    -0.76
    POSITIVE LOGITS
    pable
    1.34
    yards
    1.30
     ship
    1.25
    íte
    1.02
    wre
    1.01
    hape
    1.00
     Ship
    1.00
    lap
    0.99
    Ship
    0.98
     hull
    0.98
    Activations Density 0.014%

    No Known Activations