© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66111
    Prev
    Next
    INDEX
    Explanations

    place names and proper nouns

    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
    ,
    -2.63
     that
    -2.16
     a
    -2.06
     in
    -1.93
     those
    -1.93
     this
    -1.87
     an
    -1.82
     which
    -1.78
     it
    -1.72
    ).
    -1.66
    POSITIVE LOGITS
    Zutaten
    1.91
     étan
    1.86
    Ingrédients
    1.84
    笮
    1.84
    Ingredi
    1.81
     mélang
    1.78
     ansik
    1.78
     många
    1.78
    Réponse
    1.77
    انواع
    1.74
    Activations Density 0.064%

    No Known Activations