© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43270
    Prev
    Next
    INDEX
    Explanations

    help

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

    The neuron fires primarily on occurrences of the standalone word “help.”

    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
    '
    -3.30
    </h2>
    -2.45
    s
    -2.27
     actually
    -2.14
    餮
    -2.09
     usually
    -2.00
    tisgarh
    -1.93
     essentially
    -1.91
    比特
    -1.91
    </td>
    -1.89
    POSITIVE LOGITS
    ﮭ
    2.41
     wth
    2.31
    before
    2.30
    ܞ
    2.22
    ではでは
    2.19
    zzlies
    2.11
    代わりに
    2.09
     magnétique
    2.09
    发展的
    2.08
    
    2.08
    Activations Density 0.020%

    No Known Activations