© 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. 92119
    Prev
    Next
    INDEX
    Explanations

    supplied, provided, published, distributed

    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
     it
    -1.20
     its
    -1.11
    でに
    -1.05
     taką
    -1.04
     their
    -1.03
     zároveň
    -1.02
    UniformLocation
    -1.01
     pareció
    -1.01
     that
    -1.00
    本事
    -0.99
    POSITIVE LOGITS
     by
    1.39
    bezpe
    1.06
     recherchez
    1.06
     bych
    1.05
    ݁
    1.04
     in
    1.03
     odkry
    1.03
     karty
    1.02
     byli
    1.02
    龶
    1.02
    Activations Density 0.201%

    No Known Activations