© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20742
    Prev
    Next
    INDEX
    Explanations

    Raheem, RAAF, Carl Sundin, Hyperolius

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

    acronyms and uppercase letter sequences at the beginning of lines.

    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_10/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
    </i>
    -2.84
    J
    -2.63
    <b>
    -2.17
     pueden
    -2.09
     сча
    -2.08
    玙
    -2.00
    屃
    -1.95
    OU
    -1.94
    ſſen
    -1.91
    蔸
    -1.91
    POSITIVE LOGITS
     be
    2.25
    捜
    2.22
    .''
    1.98
    летия
    1.98
    の絵
    1.92
     esclusivamente
    1.84
     are
    1.84
    Santé
    1.79
    はこんな感じ
    1.78
     prodot
    1.77
    Activations Density 0.000%

    No Known Activations