© 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. 113101
    Prev
    Next
    INDEX
    Explanations

    alfalfa hay

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

    the word "espresso" and agriculture-related terms like "alfalfa".

    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
     Their
    -3.56
    </td>
    -2.78
    </b>
    -2.72
    🧌
    -2.67
    𖤍
    -2.58
    又在
    -2.47
    
    -2.41
    ꦢ
    -2.39
     execução
    -2.38
    🛇
    -2.36
    POSITIVE LOGITS
    “
    2.44
    For
    2.36
    ,
    2.13
    *
    2.06
    ↵
    2.03
    ется
    1.88
     він
    1.87
    ↵↵
    1.87
     so
    1.86
    婓
    1.85
    Activations Density 0.001%

    No Known Activations