© 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. 71708
    Prev
    Next
    INDEX
    Explanations

    cherish or treasure

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

    The neuron activates on occurrences of the root “cher” (as in cherish, cherished, cherishes, 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_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
    釭
    -2.44
    ឵
    -2.39
     baterie
    -2.39
    
    -2.34
     prossima
    -2.31
    鰨
    -2.28
    戆
    -2.28
     It
    -2.28
     When
    -2.25
    ⎆
    -2.25
    POSITIVE LOGITS
    ’
    2.89
    {
    2.78
    that
    2.63
    "
    2.53
    ,.
    2.47
     I
    2.36
    1
    2.30
    ным
    2.13
    又不
    2.13
     
    2.05
    Activations Density 0.002%

    No Known Activations