© 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. 22-GEMMASCOPE-RES-131K
    7. 72889
    Prev
    Next
    INDEX
    Explanations

    connecting different concepts

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

    The neuron fires on segments containing numeric or quantitative information—figures, counts, stats, and their immediate context.

    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
     objs
    -0.89
    きに
    -0.85
    })-
    -0.82
     deviennent
    -0.82
     aplique
    -0.81
    его
    -0.81
     inappropriés
    -0.80
    マッサージ
    -0.79
    agerie
    -0.79
    वं
    -0.79
    POSITIVE LOGITS
     private
    1.18
    Our
    1.04
     local
    0.95
     independently
    0.93
    ecirc
    0.91
     grassroots
    0.90
     internal
    0.90
     independent
    0.88
    estias
    0.88
    ．．
    0.87
    Activations Density 0.141%

    No Known Activations