© 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. 34-GEMMASCOPE-RES-131K
    7. 33198
    Prev
    Next
    INDEX
    Explanations

    wanting to know

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

    The neuron activates on numeric tokens (multi‐digit numbers) 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_34/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
     novios
    -0.99
     frontières
    -0.94
    えました
    -0.93
    ρου
    -0.93
     líquidos
    -0.92
    athen
    -0.91
    ztés
    -0.90
    zoeken
    -0.90
     большин
    -0.90
     computadoras
    -0.88
    POSITIVE LOGITS
     know
    1.52
     any
    1.51
     opinions
    1.45
     if
    1.36
     your
    1.30
     hear
    1.30
     anyone
    1.21
     peoples
    1.16
     suggestions
    1.15
     confirmation
    1.09
    Activations Density 0.272%

    No Known Activations