© 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. 7794
    Prev
    Next
    INDEX
    Explanations

    saving lives, money, time

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

    The neuron consistently activates on occurrences of the word “save” and its inflected forms (e.g. “saving”).

    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
    ꪔ
    -1.83
    鐧
    -1.69
     MAKES
    -1.67
    phoned
    -1.67
    婠
    -1.66
    
    -1.64
    檮
    -1.63
     nový
    -1.63
     využí
    -1.59
    方で
    -1.59
    POSITIVE LOGITS
    {
    2.13
    {
    2.00
    c
    1.81
    if
    1.80
    ].
    1.77
    ]:
    1.73
    <h2>
    1.70
    .’
    1.66
    that
    1.65
    </h1>
    1.64
    Activations Density 0.011%

    No Known Activations