© 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. 22-GEMMASCOPE-RES-131K
    7. 95341
    Prev
    Next
    INDEX
    Explanations

    biological and time units

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

    data points and statistical measurements in research papers and reports.

    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_22/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
     what
    -1.13
    heiros
    -0.93
     präsenti
    -0.91
     дли
    -0.91
     membri
    -0.91
     wußte
    -0.91
    Hvad
    -0.90
     beschäf
    -0.89
     calciatore
    -0.87
     suchte
    -0.86
    POSITIVE LOGITS
     bandoulière
    1.03
    ったのは
    1.02
    与此同时
    0.98
    始めて
    0.97
    ffective
    0.97
    があり
    0.97
    🎦
    0.96
    гласно
    0.95
    プロセス
    0.94
    があります
    0.93
    Activations Density 0.108%

    No Known Activations