© 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. 74951
    Prev
    Next
    INDEX
    Explanations

    describing contents

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

    The neuron strongly activates on the word “contains.”

    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
    also
    -2.64
    鲠
    -2.42
    ſam
    -2.34
     они
    -2.34
    ♨
    -2.25
    gefügt
    -2.20
    𓐍
    -2.19
    齤
    -2.16
     câteva
    -2.13
    ꦢ
    -2.13
    POSITIVE LOGITS
    ).
    3.08
     irritated
    2.47
     It
    2.42
    *.
    2.36
    修復
    2.28
    </h3>
    2.28
    </strong>
    2.25
     them
    2.22
    法則
    2.20
    ings
    2.19
    Activations Density 0.029%

    No Known Activations