© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37712
    Prev
    Next
    INDEX
    Explanations

    reaching a degree or limit

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

    This neuron detects occurrences of the word “point,” especially in the phrase “to the point.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     trám
    -0.99
    secara
    -0.90
    rences
    -0.89
     素描
    -0.88
    íticos
    -0.88
     prenda
    -0.88
    essentially
    -0.87
    킁
    -0.87
     Avec
    -0.87
     tormenta
    -0.86
    POSITIVE LOGITS
     that
    2.73
     where
    2.14
     of
    1.88
     it
    1.36
     when
    1.17
     whereby
    1.13
     at
    1.12
     even
    1.09
    Even
    1.05
    حيث
    1.03
    Activations Density 0.016%

    No Known Activations