© 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. 103903
    Prev
    Next
    INDEX
    Explanations

    things described as meaningful

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

    The neuron specifically detects occurrences of the word “meaningful.”

    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
    ケモン
    -2.39
     Heilige
    -2.27
     maravill
    -2.17
    ";
    -2.16
     escucha
    -2.16
     guapos
    -2.13
    廛
    -2.09
     置物
    -2.06
    archiwizowane
    -2.05
     verdaderos
    -2.05
    POSITIVE LOGITS
    </em>
    3.17
    '
    2.91
    *
    2.70
    </h4>
    2.63
    n
    2.53
    d
    2.33
    就行
    2.23
    s
    2.23
    ஂ
    2.09
     meaningful
    2.05
    Activations Density 0.004%

    No Known Activations