© 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. 10584
    Prev
    Next
    INDEX
    Explanations

    modern agriculture

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

    misspelled or unusual typographical elements in formal documents.

    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
     juste
    -1.91
    笮
    -1.66
     votre
    -1.59
    髫
    -1.51
    
    -1.49
     ون
    -1.48
     infek
    -1.48
    臯
    -1.47
     discut
    -1.47
     creer
    -1.46
    POSITIVE LOGITS
     when
    1.46
     Compared
    1.46
     Polskiego
    1.44
     for
    1.41
    :
    1.38
    boné
    1.36
    weebly
    1.34
     or
    1.30
     This
    1.28
     during
    1.28
    Activations Density 0.165%

    No Known Activations