© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73218
    Prev
    Next
    INDEX
    Explanations

    education, history, process, stories

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

    This neuron fires strongly on semantically rich, topic-specific content words (especially nouns and verbs) that signal the main subject or domain being discussed.

    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
    They
    -1.79
     they
    -1.76
     or
    -1.73
     this
    -1.70
     them
    -1.66
     their
    -1.58
    他们
    -1.44
     these
    -1.43
     их
    -1.39
    其他
    -1.38
    POSITIVE LOGITS
    辎
    1.61
    ведение
    1.51
    もあって
    1.48
     flesta
    1.46
    Médaille
    1.45
    belast
    1.38
     alſo
    1.38
    photographe
    1.35
    krę
    1.34
    śnia
    1.34
    Activations Density 0.156%

    No Known Activations