© 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. 111613
    Prev
    Next
    INDEX
    Explanations

    polymers containing imine or ethylenimine groups

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

    scientific or technical terminology in academic or research contexts.

    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
     and
    -2.44
    dersfield
    -2.14
     zahlreiche
    -2.05
    istungen
    -1.88
     aanz
    -1.84
     ผม
    -1.83
    úcia
    -1.80
     enamorado
    -1.76
     görd
    -1.74
    there
    -1.72
    POSITIVE LOGITS
     meisten
    2.11
     müsse
    1.98
     manhã
    1.81
     müsste
    1.78
    """
    1.78
     werde
    1.73
    u
    1.72
    >
    1.72
    我一直
    1.72
    .."
    1.71
    Activations Density 0.514%

    No Known Activations