© 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. 22-GEMMASCOPE-RES-131K
    7. 35440
    Prev
    Next
    INDEX
    Explanations

    PRDM9 gene/protein

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

    legal documents, specifically court cases, with numbered lines and formal formatting.

    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_22/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
     this
    -1.34
     its
    -1.34
     not
    -1.27
     any
    -1.22
     many
    -1.20
     more
    -1.18
     using
    -1.16
     several
    -1.12
     use
    -1.05
    넌
    -1.04
    POSITIVE LOGITS
    itati
    1.23
    alians
    1.19
    Instead
    1.16
    菒
    1.11
    ebly
    1.11
    licopter
    1.10
    hese
    1.06
    unno
    1.06
    ͛
    1.06
    acular
    1.05
    Activations Density 0.000%

    No Known Activations