© 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. 9367
    Prev
    Next
    INDEX
    Explanations

    temporary or provisional states

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

    The neuron fires strongly on any token containing the substring “temp” (e.g. temp, temporary, TempString).

    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
    鹛
    -1.45
    XCTAssertEqual
    -1.24
    える
    -1.21
    詬
    -1.21
    swald
    -1.19
     niya
    -1.17
    responseData
    -1.16
     menino
    -1.16
     essentielle
    -1.16
     byen
    -1.14
    POSITIVE LOGITS
     that
    1.48
    ↵↵
    1.38
     my
    1.34
     last
    1.31
     nasz
    1.26
    があった
    1.25
    一時
    1.24
     things
    1.23
    意思
    1.21
     entusiasmo
    1.20
    Activations Density 0.086%

    No Known Activations