© 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. 91359
    Prev
    Next
    INDEX
    Explanations

    InitializeComponent

    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
     had
    -0.89
     on
    -0.80
     fjor
    -0.78
    toner
    -0.78
    》（
    -0.77
     Australien
    -0.77
     usai
    -0.77
     Eğ
    -0.77
     from
    -0.76
     two
    -0.76
    POSITIVE LOGITS
    inematic
    0.94
    }}+\
    0.90
    ビタ
    0.89
     dringend
    0.83
     thermoc
    0.83
    aptors
    0.82
     партии
    0.82
    calipsis
    0.82
    indrome
    0.81
     버튼
    0.81
    Activations Density 0.000%

    No Known Activations