© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44978
    Prev
    Next
    INDEX
    Explanations

    eukaryotic and prokaryotic cells

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

    terms related to biological cells and organisms, particularly identifying prokaryotic and eukaryotic classifications.

    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
    ?"
    -2.28
    ."
    -2.17
     was
    -2.03
    ",
    -1.99
    ',
    -1.73
    ="
    -1.66
     have
    -1.64
    。“
    -1.64
    -
    -1.58
     \'
    -1.52
    POSITIVE LOGITS
    ástica
    1.88
    慙
    1.72
     WITH
    1.71
    ∻
    1.71
     邸
    1.70
     nevoie
    1.66
    setViewName
    1.66
    桖
    1.66
     schnellen
    1.65
     皇族
    1.63
    Activations Density 0.030%

    No Known Activations