© 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. 22-GEMMASCOPE-RES-131K
    4. 68942
    Prev
    Next
    INDEX
    Explanations

    removing unwanted substances and excess

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

    materials or substances being removed, extracted, or eliminated from something.

    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
     verhe
    -1.38
     boe
    -1.36
     internationales
    -1.25
     tungkol
    -1.23
    ÚBL
    -1.20
    āja
    -1.18
     methode
    -1.18
     verst
    -1.12
     departement
    -1.12
     республи
    -1.12
    POSITIVE LOGITS
     any
    1.78
     some
    1.48
     those
    1.47
     both
    1.39
     that
    1.38
     everything
    1.34
     previous
    1.32
     specchio
    1.27
     excess
    1.27
     excessive
    1.27
    Activations Density 0.044%

    No Known Activations