© 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. 1026
    Prev
    Next
    INDEX
    Explanations

    UIColor and reuse

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

    the word "Reuse" or variations like "reuse" in programming and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    \
    -4.03
    1
    -3.09
    就不是
    -2.88
     случаях
    -2.59
     //
    -2.53
     mientras
    -2.52
    si
    -2.50
    ]
    -2.44
     niż
    -2.41
    幸好
    -2.41
    POSITIVE LOGITS
    鲼
    2.33
    ⃚
    2.28
     Mischung
    2.28
     OUTER
    2.22
    ે
    2.22
    e
    2.16
    ✝
    2.16
     REAR
    2.16
     praktische
    2.14
     ";
    2.11
    Activations Density 0.007%

    No Known Activations