© 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. 87050
    Prev
    Next
    INDEX
    Explanations

    personal own something

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

    The neuron fires on occurrences of the word “personal.”

    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
     ganó
    -1.66
     asesinado
    -1.64
     mencegah
    -1.63
     memungkinkan
    -1.48
     sentada
    -1.47
     mencionados
    -1.39
     compró
    -1.39
    冏
    -1.38
     kepentingan
    -1.37
     personalizadas
    -1.36
    POSITIVE LOGITS
    i
    1.59
    </em>
    1.55
    y
    1.48
    be
    1.42
     INDUSTR
    1.36
    ">/
    1.36
    و
    1.35
    j
    1.34
    have
    1.33
     ـ
    1.33
    Activations Density 0.021%

    No Known Activations