© 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. 73603
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

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

    The neuron activates on uppercase acronyms and initialisms (e.g., measurement units and disease or technical abbreviations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ⚋
    -2.77
    ꯸
    -2.47
    );
    -2.45
    能夠
    -2.36
    ).
    -2.31
     For
    -2.27
     '>=
    -2.20
    1
    -2.19
    StoryboardSegue
    -2.19
     That
    -2.19
    POSITIVE LOGITS
    鲧
    2.47
     दुनिया
    2.22
     of
    2.09
    
    2.09
     numerosos
    2.05
    ↵↵
    2.05
     лучших
    2.05
    lde
    2.05
     zöld
    2.05
     entornos
    2.02
    Activations Density 0.076%

    No Known Activations