© 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. 15021
    Prev
    Next
    INDEX
    Explanations

    extra boost or benefit

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

    The neuron fires on occurrences of the intensifier “extra” (and its close variants in promotional “go the extra mile,” “little extra boost,” “extra special,” etc.).

    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
    .
    -1.57
     pronti
    -1.52
     ogrom
    -1.31
     and
    -1.27
     Instead
    -1.27
     Accordingly
    -1.27
     afrontar
    -1.23
     Currently
    -1.23
    lemek
    -1.23
    ,
    -1.21
    POSITIVE LOGITS
     \
    1.59
    ।
    1.52
     fotográfica
    1.52
    黾
    1.50
     different
    1.49
     chilena
    1.48
     kombiniert
    1.48
     realizada
    1.48
     bendera
    1.48
     necessários
    1.47
    Activations Density 0.021%

    No Known Activations