© 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. 10-GEMMASCOPE-RES-131K
    4. 41965
    Prev
    Next
    INDEX
    Explanations

    parasitic stages or life cycles

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

    biological or scientific terms related to cell structures, embryonic development, and life stages.

    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
     then
    -2.05
     and
    -1.59
    itored
    -1.49
    if
    -1.47
     blumen
    -1.46
    createElement
    -1.45
    1
    -1.41
    moreland
    -1.38
     gemeenten
    -1.38
     But
    -1.36
    POSITIVE LOGITS
     encantó
    1.48
    🩴
    1.39
    了吗
    1.38
     borracha
    1.38
     gustaba
    1.38
     celulares
    1.36
    𝗙
    1.36
     impetus
    1.35
     где
    1.35
     unduly
    1.34
    Activations Density 0.108%

    No Known Activations