© 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. 33499
    Prev
    Next
    INDEX
    Explanations

    terms followed by specific items

    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
    יצוני
    -0.84
    ipient
    -0.82
     hohem
    -0.81
    ursday
    -0.81
    ➁
    -0.81
     OSError
    -0.80
     หลวง
    -0.80
    ++$
    -0.79
    requency
    -0.78
    urrent
    -0.77
    POSITIVE LOGITS
     både
    1.49
     entities
    1.45
     everything
    1.37
     either
    1.34
     amenities
    1.32
     anything
    1.30
     things
    1.27
    无论是
    1.27
     items
    1.24
     stuff
    1.24
    Activations Density 0.392%

    No Known Activations