© 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. 34939
    Prev
    Next
    INDEX
    Explanations

    court filings

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

    This neuron fires on numeric tokens—especially multi‐digit numbers used in formatted tables or document headings.

    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
     only
    -1.48
    Only
    -1.30
     burgeoning
    -1.18
    Despite
    -1.13
    People
    -1.11
    Two
    -1.11
     Although
    -1.09
    Although
    -1.09
     started
    -1.06
    Because
    -1.06
    POSITIVE LOGITS
     francus
    1.24
     !!!!
    1.20
    ï
    1.13
    
    1.13
    Ï
    1.13
    Ŏ
    1.12
     äl
    1.10
     pyta
    1.08
     hrab
    1.08
     heilige
    1.07
    Activations Density 0.011%

    No Known Activations