© 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. 10-GEMMASCOPE-RES-131K
    7. 44308
    Prev
    Next
    INDEX
    Explanations

    Dial A Deal, Duane, Error, Web

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

    The neuron primarily fires on numeric tokens (especially numeric literals 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_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
    despite
    -1.40
     médecins
    -1.38
     ähnliche
    -1.30
     escritório
    -1.30
    
    -1.29
     enseignants
    -1.29
     aluguel
    -1.28
     pinak
    -1.27
    ungkapkan
    -1.26
    unfortunately
    -1.26
    POSITIVE LOGITS
    Those
    1.74
    That
    1.59
    With
    1.45
     Those
    1.45
    For
    1.40
    They
    1.35
     Nearly
    1.32
    During
    1.31
     With
    1.29
     but
    1.26
    Activations Density 0.001%

    No Known Activations