© 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. 14395
    Prev
    Next
    INDEX
    Explanations

    distorting or distortion

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

    The neuron activates on words (or word fragments) related to distortion or obscuring (e.g. “distort,” “distorting,” “distorted,” “obscuring”).

    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
    跸
    -1.85
     hæ
    -1.63
    圧倒
    -1.54
    不下
    -1.53
    ならない
    -1.53
     correto
    -1.53
     schrift
    -1.52
     chão
    -1.52
     folhe
    -1.51
    
    -1.51
    POSITIVE LOGITS
    ↵
    2.17
    </h4>
    1.63
    ᩠
    1.58
     kuiten
    1.57
    </em>
    1.57
     if
    1.54
     twisting
    1.51
    ᎑
    1.48
     läsa
    1.47
     być
    1.45
    Activations Density 0.060%

    No Known Activations