© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40703
    Prev
    Next
    INDEX
    Explanations

    few or many followed by a noun

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

    The neuron is specialized to detect numeric tokens and numeric values (both integers and decimals) in the text.

    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
    )));
    -1.42
    );
    
    -1.34
    )).
    -1.34
    ));
    -1.30
    </sup>
    -1.27
    }}=\
    -1.27
    войства
    -1.25
    =*/
    -1.24
    âng
    -1.23
    日閲覧
    -1.22
    POSITIVE LOGITS
    将他
    1.23
     argint
    1.17
     furia
    1.16
     deß
    1.11
     verir
    1.09
     marea
    1.07
    なと
    1.06
     údaj
    1.05
     equit
    1.05
     适合
    1.03
    Activations Density 0.045%

    No Known Activations