© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73290
    Prev
    Next
    INDEX
    Explanations

    amino-acid residues or needs

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

    compound nouns and hyphenated terms, particularly related to technical or specialized terms.

    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
     –
    -1.87
    ཋ
    -1.54
     =
    -1.52
    垻
    -1.49
     erzä
    -1.48
     первый
    -1.44
    s
    -1.43
     не
    -1.43
    について
    -1.42
     може
    -1.41
    POSITIVE LOGITS
     melap
    1.90
    鹀
    1.87
     zoek
    1.85
     memutus
    1.80
    🫓
    1.70
     mengucap
    1.66
    
    1.58
     reizen
    1.57
     wijk
    1.57
     quels
    1.57
    Activations Density 0.120%

    No Known Activations