© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6756
    Prev
    Next
    INDEX
    Explanations

    born and passed away

    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
     già
    -0.95
    🧃
    -0.90
     |]
    -0.90
    presents
    -0.85
     plc
    -0.84
    田市
    -0.83
    :))
    -0.83
     }))
    -0.82
    емых
    -0.82
     that
    -0.81
    POSITIVE LOGITS
     olabilir
    1.14
     после
    1.13
     born
    1.05
     passed
    1.02
     Nachteile
    1.02
     died
    0.99
     (“
    0.99
     gesetzlichen
    0.97
     was
    0.94
     даже
    0.94
    Activations Density 0.029%

    No Known Activations