© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63167
    Prev
    Next
    INDEX
    Explanations

    common word followed by specific context

    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
     свети
    -0.99
     contextLoads
    -0.81
     someday
    -0.79
    cún
    -0.79
     продукти
    -0.77
    لاس
    -0.76
     when
    -0.75
    uuuuu
    -0.75
     oftentimes
    -0.75
    mallow
    -0.75
    POSITIVE LOGITS
    particularly
    0.98
    perhaps
    0.97
    became
    0.94
     relevante
    0.93
    kehren
    0.90
    ─
    0.88
    Numerade
    0.88
     toute
    0.87
    began
    0.87
    offered
    0.86
    Activations Density 0.005%

    No Known Activations