© 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. 22-GEMMASCOPE-RES-131K
    7. 39369
    Prev
    Next
    INDEX
    Explanations

    philosophy of

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

    The neuron activates on occurrences of the word “philosophy” (and its close morphological variants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ࿚
    -2.34
     proporciona
    -2.34
    t
    -2.31
    跸
    -2.20
     What
    -2.20
    齜
    -2.13
    に関して
    -2.13
    大半
    -2.11
    …)
    -2.09
    Donativos
    -2.08
    POSITIVE LOGITS
    .
    3.44
    圌
    3.13
     of
    2.58
    ſſen
    2.56
    และ
    2.50
    ”،
    2.45
    Wife
    2.41
    鸸
    2.23
    煦
    2.19
     gavetas
    2.16
    Activations Density 0.005%

    No Known Activations