© 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. 21404
    Prev
    Next
    INDEX
    Explanations

    recognized entities and phrases

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

    The neuron is primarily activated by numeric tokens—especially standalone numbers and decimal values.

    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
    ),
    -2.17
     hesitation
    -2.02
     diantaranya
    -1.93
     caters
    -1.82
     regard
    -1.78
    َا
    -1.75
    v
    -1.70
     comienzan
    -1.70
     ней
    -1.68
     fondness
    -1.67
    POSITIVE LOGITS
    퐶
    2.30
    𖣘
    2.22
    噚
    2.17
    髎
    2.13
     för
    2.09
    媖
    2.06
    緜
    2.03
    燾
    2.03
    锨
    2.00
    acterísticas
    1.98
    Activations Density 0.000%

    No Known Activations