© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25860
    Prev
    Next
    INDEX
    Explanations

    women's health

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

    page numbers in technical or legal documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the presence of numeric tokens (sequences of digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     one
    -0.97
     but
    -0.96
     or
    -0.95
     did
    -0.94
     do
    -0.94
    ㎞
    -0.88
    ……」
    -0.88
     other
    -0.87
     bois
    -0.82
     medel
    -0.81
    POSITIVE LOGITS
    avantage
    1.02
     opnieuw
    1.02
     chickpeas
    1.02
     ponownie
    0.96
     again
    0.96
    alimentation
    0.94
     publiek
    0.94
    ₭
    0.94
    ypeł
    0.94
     prachtige
    0.92
    Activations Density 0.000%

    No Known Activations