© 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. 100467
    Prev
    Next
    INDEX
    Explanations

    Sports, names, categories

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

    This neuron is tuned to spot numeric tokens and statistical figures (especially decimal numbers and scores).

    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
     by
    -1.50
    малар
    -1.17
    新作
    -1.09
    
    -1.05
     wilder
    -1.05
    ？』
    -1.02
    インストール
    -1.02
    าศ
    -1.01
     imagine
    -1.00
     not
    -0.99
    POSITIVE LOGITS
     pozna
    1.22
    ůvod
    1.15
     franchises
    1.08
    deutsch
    1.06
    crire
    1.06
     poby
    1.03
    瀹
    1.03
    vertible
    1.03
    ОВО
    1.03
     cierre
    1.02
    Activations Density 0.024%

    No Known Activations