© 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. 82257
    Prev
    Next
    INDEX
    Explanations

    lung cancer

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

    sentence starters or transition phrases that begin explanatory paragraphs.

    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
    Économie
    -1.05
    €“
    -0.97
    Highly
    -0.96
    ेमाल
    -0.95
     and
    -0.93
    attendre
    -0.92
    Tue
    -0.91
    立
    -0.91
    Интере
    -0.91
    openqa
    -0.90
    POSITIVE LOGITS
     possibilidade
    1.11
     conceivably
    1.07
     bibliothèque
    1.02
     mód
    0.98
    ixels
    0.98
    )
    0.97
     должен
    0.96
    に関しては
    0.95
     calça
    0.94
     thereupon
    0.91
    Activations Density 0.002%

    No Known Activations