© 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. 58929
    Prev
    Next
    INDEX
    Explanations

    markup declarations and source code

    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
     their
    -0.91
     many
    -0.84
     unrelenting
    -0.84
    šenie
    -0.82
     meticulously
    -0.82
    énération
    -0.82
     meticulous
    -0.81
     furthering
    -0.77
     lipca
    -0.76
     psychotic
    -0.75
    POSITIVE LOGITS
     gigantic
    1.02
     praticamente
    0.94
    particularly
    0.91
     イエロー
    0.90
     deux
    0.88
     impromptu
    0.86
    LOYEES
    0.86
     geprüft
    0.85
     unbelievably
    0.84
    ancien
    0.84
    Activations Density 0.000%

    No Known Activations