© 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. 45012
    Prev
    Next
    INDEX
    Explanations

    describing a topic

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

    The neuron flags occurrences of the standalone word “Describe” (e.g. in headings or function names).

    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
    厹
    -2.48
    ='
    -2.42
     '
    -2.33
    也
    -2.31
    zembro
    -2.31
    旆
    -2.28
    mathrm
    -2.22
    ৢ
    -2.13
    们的
    -2.13
     ་
    -2.13
    POSITIVE LOGITS
    u
    2.39
    前は
    2.05
    墬
    2.03
    vantaged
    2.03
    新能源
    1.99
     assessing
    1.98
     demonstrate
    1.93
     *
    1.92
     which
    1.91
    UREAU
    1.91
    Activations Density 0.013%

    No Known Activations