© 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. 25904
    Prev
    Next
    INDEX
    Explanations

    constraint

    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
     was
    -1.54
    🧌
    -1.20
    鑁
    -1.10
    FixedSize
    -1.07
     atualizar
    -1.05
     hóspedes
    -1.05
     transcends
    -1.05
    呶
    -1.05
    steuer
    -1.02
    ization
    -1.01
    POSITIVE LOGITS
     imposed
    1.34
    T
    1.07
    con
    1.05
     Con
    1.00
     violation
    1.00
    ).
    0.98
    in
    0.98
     on
    0.96
     たん
    0.96
    🧭
    0.96
    Activations Density 0.008%

    No Known Activations