© 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. 73296
    Prev
    Next
    INDEX
    Explanations

    magnetic field, physiology

    np_acts-logits-general · gemini-2.5-flash-lite

    instances where there is a negative index in array or string access operations (like [-1] or tail -1).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    esos
    -0.96
     during
    -0.96
    車は
    -0.94
    螂
    -0.92
     mainly
    -0.91
    حن
    -0.90
    NonUser
    -0.90
     aldrig
    -0.89
    ằ
    -0.88
    翌日
    -0.87
    POSITIVE LOGITS
    most
    0.82
     izan
    0.82
     QUAL
    0.79
    ною
    0.78
    last
    0.75
    ACCESS
    0.75
     ders
    0.74
     gasp
    0.74
     ortodo
    0.73
     ideolog
    0.73
    Activations Density 0.004%

    No Known Activations