© 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. 75592
    Prev
    Next
    INDEX
    Explanations

    journal article alerts or citations

    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
     using
    -0.81
     those
    -0.76
    auru
    -0.75
     universally
    -0.75
     even
    -0.74
    大学の
    -0.72
     possibly
    -0.71
     exc
    -0.71
    прият
    -0.71
     many
    -0.70
    POSITIVE LOGITS
    ervious
    0.88
     séjours
    0.86
     referee
    0.85
     =='
    0.84
    Celebrate
    0.84
    iul
    0.84
     FORD
    0.83
    Moth
    0.82
    kia
    0.82
    媄
    0.82
    Activations Density 0.003%

    No Known Activations