© 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. 4224
    Prev
    Next
    INDEX
    Explanations

    locations and geography

    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
     now
    -1.38
     hitherto
    -1.30
     voorbeeld
    -1.20
     newly
    -1.16
     presently
    -1.16
     hochwer
    -1.15
     工場
    -1.13
     bubuk
    -1.10
     дуже
    -1.07
    んだん
    -1.07
    POSITIVE LOGITS
     locals
    1.40
     pittores
    1.28
     residents
    1.23
     ​​
    1.23
    History
    1.16
    Cannot
    1.09
     LGBTQ
    1.09
     Instagram
    1.08
    ‌
    1.07
     Tarif
    1.05
    Activations Density 0.064%

    No Known Activations