© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86579
    Prev
    Next
    INDEX
    Explanations

    many, much, lot, bastante, muito

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

    The neuron activates on degree words and quantifiers expressing large amount or intensity (e.g. “muito,” “muitas,” “bastante,” “grande”).

    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
    圌
    -2.42
     dando
    -2.36
    褙
    -2.31
    拶
    -2.30
    馘
    -2.27
    栳
    -2.25
    镲
    -2.09
    蠖
    -2.09
     continúas
    -2.08
    
    -2.08
    POSITIVE LOGITS
    <bos>
    2.45
     enhances
    2.33
     Sadly
    2.33
     Before
    2.30
    );
    2.28
     Surprisingly
    2.17
     (>
    2.17
     Both
    2.11
    );
    2.09
     Depending
    2.09
    Activations Density 0.003%

    No Known Activations