© 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. 100435
    Prev
    Next
    INDEX
    Explanations

    legal case citation elements

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

    This neuron specializes in spotting long runs of leading whitespace or indentation 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
    </em>
    -1.73
     století
    -1.60
    ˗
    -1.51
    –
    -1.51
    +}$
    -1.50
    𝑛
    -1.45
    ть
    -1.44
    Other
    -1.43
     egyéb
    -1.43
    UCIÓN
    -1.41
    POSITIVE LOGITS
     prega
    1.89
     have
    1.81
     comunica
    1.71
     continuare
    1.70
    1
    1.60
     are
    1.54
     prossima
    1.53
     zů
    1.50
     epidem
    1.50
    的主要
    1.50
    Activations Density 0.005%

    No Known Activations