© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71703
    Prev
    Next
    INDEX
    Explanations

    birth related terms

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

    references to birth or birth-related data in academic, medical, or statistical 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_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
    the
    -2.95
    熥
    -2.20
    vial
    -2.09
    部分が
    -2.08
    埽
    -2.05
     he
    -2.02
    塒
    -1.97
    蚡
    -1.95
    die
    -1.95
     murs
    -1.94
    POSITIVE LOGITS
     He
    2.16
     Unglück
    2.14
     Erinner
    2.13
     wiederhol
    2.08
     They
    2.08
    Four
    2.05
     Gutes
    2.05
     ähn
    2.05
     zusätz
    2.03
     zweimal
    2.03
    Activations Density 0.016%

    No Known Activations