© 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. 14553
    Prev
    Next
    INDEX
    Explanations

    mirrors

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

    This neuron detects mentions of “mirror” (and its plural/compound forms) 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
    7
    -1.52
    6
    -1.51
    <td>
    -1.49
     about
    -1.43
    完全
    -1.42
    ッカー
    -1.38
    cún
    -1.38
    1
    -1.38
     vraiment
    -1.35
    4
    -1.34
    POSITIVE LOGITS
    🪞
    1.70
     these
    1.70
    　　　　　　　　
    1.52
     $\&$
    1.47
     Mirrors
    1.47
     our
    1.45
    我这
    1.40
    ᭡
    1.34
    لوار
    1.34
    　　　　　　　
    1.34
    Activations Density 0.010%

    No Known Activations