© 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. 102393
    Prev
    Next
    INDEX
    Explanations

    possible to guess

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

    The neuron spots occurrences of the adjectives “possible” or “impossible” (often with the following “to”), i.e. expressions of possibility or impossibility.

    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
    Etimología
    -1.78
    ࿆
    -1.67
    裒
    -1.67
    佧
    -1.66
    っそ
    -1.66
     gustado
    -1.64
    רום
    -1.64
     traducciones
    -1.64
    
    -1.64
     gebruikt
    -1.63
    POSITIVE LOGITS
    {
    2.78
    勿論
    1.59
    at
    1.59
    </h4>
    1.55
     một
    1.52
    e
    1.52
     October
    1.48
    re
    1.46
    naments
    1.41
     August
    1.37
    Activations Density 0.004%

    No Known Activations