© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54004
    Prev
    Next
    INDEX
    Explanations

    leading / premier / best

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

    The neuron activates on large numerical values—especially multi-digit statistics or counts—used in marketing or informational contexts.

    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
     but
    -1.21
     preescolar
    -1.09
    værende
    -1.07
     particular
    -1.05
     usually
    -1.05
     during
    -1.05
     aprendiz
    -1.03
    釐
    -1.03
     either
    -1.02
    óri
    -1.02
    POSITIVE LOGITS
     duquel
    1.09
     behar
    0.99
     connues
    0.98
     beren
    0.97
     tiegħek
    0.97
     référence
    0.96
    верь
    0.96
     SERVICES
    0.96
     conç
    0.96
     idee
    0.95
    Activations Density 0.072%

    No Known Activations