© 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. 1777
    Prev
    Next
    INDEX
    Explanations

    faithful, faithfully, faithfulness

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

    The neuron detects occurrences of the word “faithful” (and its variant “faithfulness”).

    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
    ↵↵
    -3.58
    徧
    -2.38
     immaculate
    -2.23
     beliebt
    -2.22
    笵
    -2.19
     variadas
    -2.16
     trabajadores
    -2.14
    colgante
    -2.14
     wundersch
    -2.13
    ocidade
    -2.13
    POSITIVE LOGITS
    you
    3.81
    s
    3.36
    at
    2.92
    man
    2.91
    its
    2.61
    Ⲉ
    2.50
    most
    2.47
    “
    2.45
    </b>
    2.44
    get
    2.44
    Activations Density 0.004%

    No Known Activations