© 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. 112350
    Prev
    Next
    INDEX
    Explanations

    square brackets, grid, lattice, foot

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

    The neuron fires on occurrences of the word “square.”

    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
    </b>
    -3.34
     The
    -3.17
     VERY
    -2.94
    栳
    -2.94
     But
    -2.86
     terrific
    -2.59
     unn
    -2.59
     immense
    -2.53
    〠
    -2.53
     ----
    -2.48
    POSITIVE LOGITS
    </h3>
    3.13
    朦
    2.84
     facilitating
    2.72
    骝
    2.70
     unrelenting
    2.70
     meticulous
    2.69
    蕺
    2.59
    dáms
    2.58
     ingrained
    2.58
    jącym
    2.55
    Activations Density 0.005%

    No Known Activations