© 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. 75116
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    籥
    -2.64
    翃
    -2.47
    獓
    -2.42
    I
    -2.42
    徜
    -2.34
    輅
    -2.30
     renowned
    -2.19
     abide
    -2.17
    蓠
    -2.16
    h
    -2.13
    POSITIVE LOGITS
     gdyż
    2.53
    謦
    2.50
     Якщо
    2.42
    赑
    2.41
     ponieważ
    2.39
     gekenn
    2.39
    ጢ
    2.38
     któ
    2.34
     verheir
    2.34
     poprzed
    2.33
    Activations Density 0.000%

    No Known Activations