© 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. 547
    Prev
    Next
    INDEX
    Explanations

    Kotlin types

    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
     companionship
    -0.82
     autorisation
    -0.82
     erős
    -0.81
    <b>
    -0.80
     ingenieros
    -0.79
     «
    -0.78
     egyszerű
    -0.78
    殒
    -0.77
     CALLED
    -0.77
    ｗｗ
    -0.77
    POSITIVE LOGITS
     тоже
    0.94
    namt
    0.87
     mør
    0.87
    roli
    0.84
     ebenfalls
    0.84
    czerw
    0.81
    皤
    0.81
    öm
    0.81
    互
    0.80
    Symp
    0.80
    Activations Density 0.046%

    No Known Activations