© 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. 22-GEMMASCOPE-RES-131K
    7. 15771
    Prev
    Next
    INDEX
    Explanations

    mirror

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

    This neuron fires on occurrences of the word “mirror” (including its plural/compound forms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     \
    -2.47
    撓
    -2.42
    )):
    -2.42
     один
    -2.28
    见的
    -2.27
     algum
    -2.23
    涜
    -2.23
    骉
    -2.22
    嶇
    -2.20
    yi
    -2.16
    POSITIVE LOGITS
    It
    2.77
    毉
    2.67
    獁
    2.64
    𞤢
    2.63
    ︓
    2.63
    銩
    2.56
    ープン
    2.56
     iſt
    2.47
    衎
    2.47
    趼
    2.41
    Activations Density 0.015%

    No Known Activations