© 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. 65155
    Prev
    Next
    INDEX
    Explanations

    point of view

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

    The neuron fires on the preposition “of” when it occurs in “point of” or “points of” constructions (e.g. “point of view,” “points of sale,” “points of care”).

    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
    {
    -2.78
    ↵↵
    -2.30
     the
    -2.30
    i
    -2.14
    >
    -2.03
    .
    -1.98
     gefährlich
    -1.93
     dilapidated
    -1.90
     merkwür
    -1.87
    I
    -1.86
    POSITIVE LOGITS
    quelize
    2.73
     ferien
    2.28
    romatic
    2.22
    銩
    2.11
     valentín
    2.09
     corrobor
    2.09
    グルト
    2.09
     ſta
    2.09
    趼
    2.08
    tembro
    2.03
    Activations Density 0.005%

    No Known Activations