© 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. 10-GEMMASCOPE-RES-131K
    7. 102378
    Prev
    Next
    INDEX
    Explanations

    ranking and ordering

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

    This neuron activates on numerical values that indicate rankings or positions (e.g., the numbers following “rank,” “ranks,” “ranked,” or similar ranking terms).

    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
     to
    -2.50
     Because
    -2.23
     Despite
    -2.19
     Basically
    -1.97
     Following
    -1.92
    )]
    -1.91
     Actually
    -1.89
     Ironically
    -1.82
     Essentially
    -1.82
     Regardless
    -1.80
    POSITIVE LOGITS
    </h4>
    1.91
    
    1.75
     opposed
    1.70
     oferec
    1.65
    1.59
     انا
    1.57
    ter
    1.55
     algum
    1.55
    䊐
    1.52
     eerste
    1.51
    Activations Density 0.014%

    No Known Activations