© 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. 16107
    Prev
    Next
    INDEX
    Explanations

    reaching a final point

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

    The neuron activates on numeric values (tokens representing numbers, including integers and decimals).

    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
     cucharadas
    -0.89
     started
    -0.88
    comple
    -0.87
    zość
    -0.83
    ories
    -0.83
    が始
    -0.82
     navideños
    -0.81
     primeiras
    -0.81
     lendemain
    -0.81
     Starts
    -0.81
    POSITIVE LOGITS
     finally
    1.73
     Finally
    1.65
    Finally
    1.54
     culminating
    1.49
     culmin
    1.41
     finalmente
    1.37
     culminated
    1.35
     schließlich
    1.34
    finally
    1.23
     finalement
    1.20
    Activations Density 0.111%

    No Known Activations