© 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. 91434
    Prev
    Next
    INDEX
    Explanations

    stacking jewelry

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

    This neuron activates on e-commerce product–marketing text—brand and product names, descriptive selling points, numeric prices and specifications.

    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
     tiden
    -0.73
    sera
    -0.70
    zmir
    -0.70
     docteur
    -0.70
     Ronald
    -0.69
     RegExp
    -0.69
     Retro
    -0.69
     Relax
    -0.68
     квадрат
    -0.67
     chromium
    -0.66
    POSITIVE LOGITS
     stacking
    1.41
     stack
    1.39
    stack
    1.38
    Stack
    1.31
     stacked
    1.30
    STACK
    1.23
     Stack
    1.20
    stacked
    1.18
     STACK
    1.13
     stacks
    1.05
    Activations Density 0.015%

    No Known Activations