© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19213
    Prev
    Next
    INDEX
    Explanations

    bending over

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

    The neuron activates strongly on words and forms related to “bend” (e.g. bend, bent, bending).

    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
    
    -2.20
    er
    -2.08
    袮
    -1.98
    le
    -1.94
    鏵
    -1.84
    /////////
    -1.82
    Ꮉ
    -1.81
    镦
    -1.80
    ٙ
    -1.73
    hhhh
    -1.73
    POSITIVE LOGITS
    哙
    2.28
    釭
    2.06
    ↵
    2.03
    蠖
    1.93
    玊
    1.91
    橚
    1.90
     :).
    1.89
    鞮
    1.87
    它们
    1.85
    艽
    1.79
    Activations Density 0.013%

    No Known Activations