© 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. 58958
    Prev
    Next
    INDEX
    Explanations

    paid for access or services

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

    The neuron activates on occurrences of the word “paid.”

    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
     of
    -3.09
    </h2>
    -2.84
    k
    -2.69
    ).
    -2.61
    p
    -2.55
    ↵↵
    -2.30
    踱
    -2.25
    沄
    -2.20
    StoryboardSegue
    -2.09
    m
    -2.09
    POSITIVE LOGITS
    猡
    2.92
    的
    2.77
    　　*
    2.70
    Since
    2.69
    How
    2.66
    淠
    2.59
    饪
    2.53
    When
    2.52
    蜴
    2.52
    From
    2.48
    Activations Density 0.006%

    No Known Activations