© 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. 105478
    Prev
    Next
    INDEX
    Explanations

    central to importance

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

    the word “central,” especially when used to indicate something is central to a topic.

    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
    停下
    -1.59
    
    -1.59
     festgestellt
    -1.57
     extremamente
    -1.56
    و
    -1.47
    THERE
    -1.45
     nombrado
    -1.45
    尽く
    -1.45
     somente
    -1.41
    戋
    -1.41
    POSITIVE LOGITS
    c
    1.48
    Харак
    1.48
     pérd
    1.41
     impor
    1.38
     but
    1.38
     $
    1.38
    んですけど
    1.36
     sombrero
    1.35
    次回は
    1.34
     monti
    1.34
    Activations Density 0.022%

    No Known Activations