© 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. 42469
    Prev
    Next
    INDEX
    Explanations

    invaluable and valuable

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

    The neuron activates on occurrences of the adjectives “valuable” or “invaluable,” highlighting praise or importance.

    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
    Suka
    -2.44
    犼
    -2.34
    鉭
    -2.28
    鐃
    -2.27
    Kuva
    -2.27
     くれ
    -2.27
    婬
    -2.25
    mpagne
    -2.25
    kové
    -2.23
     晒
    -2.22
    POSITIVE LOGITS
    T
    2.73
    鹇
    2.73
     
    2.63
     was
    2.55
    鸶
    2.53
    EST
    2.50
    this
    2.41
     como
    2.39
    爻
    2.38
    new
    2.33
    Activations Density 0.004%

    No Known Activations