© 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. 60470
    Prev
    Next
    INDEX
    Explanations

    the end of statements

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

    The neuron is detecting decimal numeric measurements (floating‐point values) in the text.

    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
    mathbf
    -1.56
    TCL
    -1.55
    ном
    -1.52
    那些
    -1.51
    <tr>
    -1.50
     bocetos
    -1.48
    ȋ
    -1.46
    १
    -1.46
    AFTER
    -1.45
    AfterClass
    -1.45
    POSITIVE LOGITS
     the
    1.91
    良いです
    1.70
    Besitos
    1.61
     모든
    1.59
     prefeitura
    1.55
    といいます
    1.50
    怎么说
    1.46
     for
    1.44
     myös
    1.41
    Cześć
    1.41
    Activations Density 0.246%

    No Known Activations