© 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. 69948
    Prev
    Next
    INDEX
    Explanations

    surfaces and areas

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

    The neuron activates on numeric measurement values—numbers denoting dimensions, counts, or other quantified data.

    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
     they
    -1.70
     Resmi
    -1.66
     komik
    -1.54
     tutup
    -1.47
     kapak
    -1.45
    komplet
    -1.44
     kompres
    -1.40
     cevap
    -1.40
     sekret
    -1.38
    katalog
    -1.35
    POSITIVE LOGITS
    <h3>
    1.52
     который
    1.44
    <td>
    1.43
    뭘
    1.42
    <tbody>
    1.36
    al
    1.35
    1.28
     людей
    1.27
     吧
    1.25
    "
    1.23
    Activations Density 0.053%
    No Known Activations