© 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. 10-GEMMASCOPE-RES-131K
    7. 69974
    Prev
    Next
    INDEX
    Explanations

    model modelmodel numbers and product codes

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

    This neuron picks out standalone numeric tokens (often with hyphens) used in technical specifications or model-number listings.

    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
     it
    -1.63
     ....
    -1.61
     .....
    -1.59
     ......
    -1.56
     have
    -1.53
    ........
    -1.48
     so
    -1.48
     on
    -1.43
    ....
    -1.41
    </strong>
    -1.39
    POSITIVE LOGITS
     bluz
    1.81
     tunik
    1.75
     camiset
    1.75
     bañera
    1.55
    𖣔
    1.54
     evenement
    1.53
     your
    1.52
     diki
    1.52
     tracción
    1.51
     는
    1.48
    Activations Density 0.055%

    No Known Activations