© 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. 67153
    Prev
    Next
    INDEX
    Explanations

    causes or results in

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

    The neuron fires on occurrences of the verb “cause” (and its inflected forms like “causes” or “caused”).

    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
    鉺
    -1.59
     ersche
    -1.47
    𐐪
    -1.45
    🢒
    -1.43
    鉿
    -1.42
    莚
    -1.41
    ⚥
    -1.41
    ･･
    -1.39
    .>
    -1.38
    没有任何
    -1.38
    POSITIVE LOGITS
     of
    1.54
                
    1.45
     same
    1.40
    ванием
    1.36
    ными
    1.34
     mismo
    1.31
    rrer
    1.25
    ш
    1.23
     send
    1.22
     送
    1.21
    Activations Density 0.028%

    No Known Activations