© 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. 10-GEMMASCOPE-RES-131K
    7. 69470
    Prev
    Next
    INDEX
    Explanations

    scrollTop and event

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

    The neuron responds to any token containing the letters “su” (in that order), whether as a standalone suffix or within a larger word.

    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
     understand
    -2.36
     If
    -2.36
    It
    -2.33
     This
    -2.28
    If
    -2.28
    
    -2.23
     Why
    -2.23
    >")
    -2.22
    ”（
    -2.20
    ');
    -2.14
    POSITIVE LOGITS
    E
    2.88
    s
    2.77
    \
    2.63
    {
    2.58
    </strong>
    2.58
     bedeckt
    2.48
    ated
    2.33
     весьма
    2.31
    C
    2.31
    _
    2.27
    Activations Density 0.001%

    No Known Activations