© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103760
    Prev
    Next
    INDEX
    Explanations

    card game context

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

    The neuron detects mentions of “card” (and its plural form) in the text.

    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
    </b>
    -1.91
    f
    -1.59
    </u>
    -1.58
    依旧
    -1.48
    。　
    -1.44
    したい
    -1.37
    l
    -1.36
     Friends
    -1.33
    k
    -1.31
     estatua
    -1.29
    POSITIVE LOGITS
     imidlertid
    1.71
    翆
    1.59
     vanskelig
    1.57
     pomysł
    1.49
    ༔
    1.48
     valgt
    1.47
    łgorzata
    1.45
     purported
    1.45
     nesten
    1.44
     zwölf
    1.41
    Activations Density 0.009%

    No Known Activations