© 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. 10-GEMMASCOPE-RES-131K
    7. 87164
    Prev
    Next
    INDEX
    Explanations

    Nord compounds and names

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

    names with the prefix "Nord" or geographical locations containing "Nord".

    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
    नलोड
    -3.47
    渽
    -3.39
    
    -3.17
    ῎
    -2.95
    
    -2.94
    晅
    -2.84
    '];
    -2.84
     parachoque
    -2.83
    ндарт
    -2.78
    '],
    -2.77
    POSITIVE LOGITS
    to
    3.78
    9
    3.58
    ра
    3.30
    2
    3.17
    —
    3.09
    3
    3.03
    a
    3.03
    (
    2.94
    5
    2.91
     are
    2.88
    Activations Density 0.002%

    No Known Activations