© 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. 34-GEMMASCOPE-RES-131K
    7. 76812
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

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

    The neuron is specialized to pick out numeric CSS measurement values (especially pixel “px” dimensions) in style declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Domen
    -0.76
     compared
    -0.76
    contexts
    -0.75
    bry
    -0.74
     pilih
    -0.73
     Historie
    -0.73
    volezza
    -0.73
    behaviors
    -0.73
    
    -0.72
     einerseits
    -0.71
    POSITIVE LOGITS
     soiled
    0.77
     Entering
    0.75
    tomb
    0.70
    Entering
    0.70
     join
    0.69
     Üniversitesi
    0.68
    Passenger
    0.65
    ichtlich
    0.65
     FC
    0.64
    UBA
    0.64
    Activations Density 0.015%

    No Known Activations