© 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. 1607
    Prev
    Next
    INDEX
    Explanations

    subject to change or revision

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

    The neuron detects disclaimer language flagging that information may change or be inaccurate—especially phrases like “subject to change without notice” or “errors or omissions.”

    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
     paradigma
    -1.39
     implica
    -1.37
     sabia
    -1.32
     teatral
    -1.29
     supera
    -1.28
    ERTA
    -1.27
     '+':
    -1.26
     ambienta
    -1.23
    ABASES
    -1.23
     sobra
    -1.23
    POSITIVE LOGITS
    1
    1.63
    1.61
    8
    1.54
    However
    1.49
    4
    1.47
    3
    1.45
    7
    1.44
     be
    1.40
    </em>
    1.39
     gewünschten
    1.38
    Activations Density 0.017%

    No Known Activations