© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89884
    Prev
    Next
    INDEX
    Explanations

    "cross" as a prefix

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

    The neuron fires on occurrences of “cross” (often as a prefix) in compound terms like crossbow, cross‐country, CrossFit, etc.

    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
     
    -0.84
    よろ
    -0.74
     though
    -0.71
     side
    -0.69
    <strong>
    -0.69
     TAR
    -0.68
    ン
    -0.67
     hol
    -0.66
    不下
    -0.66
    有り
    -0.66
    POSITIVE LOGITS
     Cross
    1.13
    overs
    1.11
    cross
    1.07
     legged
    1.06
     Country
    1.06
     pollination
    1.05
    fade
    1.04
    Cross
    0.99
     cros
    0.97
    breed
    0.96
    Activations Density 0.030%

    No Known Activations