© 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. 7357
    Prev
    Next
    INDEX
    Explanations

    not the only

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

    The neuron is chiefly detecting the occurrence of the word “only.”

    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
     actually
    -1.49
     Bot
    -1.41
     Thursday
    -1.38
    ANTAGE
    -1.37
    alamualaikum
    -1.37
    某些
    -1.36
    Descriere
    -1.34
     Quad
    -1.32
    omores
    -1.30
     gesagt
    -1.29
    POSITIVE LOGITS
     رعایت
    1.49
     emblema
    1.41
     yetu
    1.37
     Sequelize
    1.35
     oft
    1.35
     likes
    1.31
    繽
    1.31
    栳
    1.30
    還會
    1.30
    </h2>
    1.30
    Activations Density 0.007%

    No Known Activations