© 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. 22-GEMMASCOPE-RES-131K
    7. 26334
    Prev
    Next
    INDEX
    Explanations

    potential to become something

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

    The neuron detects numeric tokens—quantities, measurements, or other number values—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_22/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
    ⌂
    -1.04
     Portugu
    -1.02
     wciąż
    -0.96
     itali
    -0.95
     soñar
    -0.95
    已經
    -0.94
    ícias
    -0.94
     kampen
    -0.93
     Arki
    -0.93
     Ducati
    -0.93
    POSITIVE LOGITS
     future
    1.86
     eventually
    1.78
     become
    1.68
     later
    1.52
     someday
    1.44
    eventually
    1.38
     if
    1.37
     great
    1.35
     eventual
    1.29
     futuras
    1.29
    Activations Density 0.032%

    No Known Activations