© 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. 70258
    Prev
    Next
    INDEX
    Explanations

    being / setting / updating / filling / displaying

    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
     κάνει
    -0.94
     используют
    -0.91
     aware
    -0.86
    )['
    -0.85
    chemise
    -0.81
     aligned
    -0.81
    とした
    -0.78
    руют
    -0.78
    setHeader
    -0.78
     práticas
    -0.77
    POSITIVE LOGITS
     being
    1.27
    водится
    1.15
     được
    1.03
    arse
    1.00
    being
    0.93
    Being
    0.93
    就被
    0.90
    都被
    0.90
    会被
    0.89
    qiu
    0.86
    Activations Density 0.020%

    No Known Activations