© 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. 80694
    Prev
    Next
    INDEX
    Explanations

    programming components and their managers

    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
     Branche
    -0.94
     especially
    -0.94
    nóstico
    -0.93
    を
    -0.90
     gern
    -0.89
     hè
    -0.89
     confianza
    -0.86
     both
    -0.86
    (!__
    -0.85
     crucero
    -0.85
    POSITIVE LOGITS
    ấc
    1.07
     död
    1.01
    Duff
    0.96
    ฯ
    0.93
     =
    0.92
     bereits
    0.87
     情報
    0.86
     EEU
    0.85
    却被
    0.85
    ellem
    0.84
    Activations Density 0.024%

    No Known Activations