© 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. 80819
    Prev
    Next
    INDEX
    Explanations

    describe blocks

    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
    IER
    -0.84
     jener
    -0.79
    ény
    -0.77
    rés
    -0.76
    なのだ
    -0.75
    ays
    -0.74
    sa
    -0.72
     مختلف
    -0.71
    tan
    -0.70
    Paused
    -0.70
    POSITIVE LOGITS
    ("
    1.29
     "
    1.16
    ('
    1.13
    」,
    1.11
     should
    0.93
    inesi
    0.90
     yapan
    0.89
     test
    0.88
     emballage
    0.88
     will
    0.87
    Activations Density 0.006%

    No Known Activations