© 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. 60544
    Prev
    Next
    INDEX
    Explanations

    doc comments with @param

    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
     unless
    -1.02
     even
    -1.00
     hanya
    -0.91
    ÃO
    -0.90
     annet
    -0.87
     pouvons
    -0.86
    edx
    -0.84
    гласно
    -0.83
     даже
    -0.83
    teams
    -0.82
    POSITIVE LOGITS
    了嗎
    0.95
    <h3>
    0.93
    fél
    0.92
     "\<
    0.86
    üstü
    0.84
     lazy
    0.82
    {\
    0.81
     Sinks
    0.81
     \"%
    0.81
    Ме
    0.80
    Activations Density 0.001%

    No Known Activations