© 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. 116504
    Prev
    Next
    INDEX
    Explanations

    place name suffixes

    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
     rusa
    -1.22
     colch
    -1.18
     elefante
    -1.06
     mosca
    -1.05
     vider
    -1.04
     leopardo
    -1.04
     ingrediente
    -1.02
    動機
    -1.01
     monumento
    -1.00
    日曜日
    -0.99
    POSITIVE LOGITS
    view
    1.53
     View
    1.42
    View
    1.23
     Hill
    1.21
    point
    1.20
     Point
    1.11
    ようになった
    1.09
     To
    1.07
    ようになる
    1.06
    wood
    1.03
    Activations Density 0.075%

    No Known Activations