© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129418
    Prev
    Next
    INDEX
    Explanations

    financial and monthly reports

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

    The neuron detects numeric measurements—especially floating‐point numbers (i.e. tokens containing digits with decimal points).

    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
     rése
    -2.03
     miniaturka
    -1.91
    傒
    -1.81
    鵙
    -1.80
     bluz
    -1.80
    
    -1.79
     charmant
    -1.79
     şal
    -1.78
    𓁹
    -1.78
     toppen
    -1.77
    POSITIVE LOGITS
     with
    2.36
     February
    2.17
     on
    2.00
     October
    1.91
     December
    1.88
     January
    1.84
     While
    1.83
     only
    1.81
     September
    1.75
     started
    1.74
    Activations Density 0.474%

    No Known Activations