© 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. 70804
    Prev
    Next
    INDEX
    Explanations

    titles and companies

    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
     dată
    -1.80
    媗
    -1.71
     barrera
    -1.63
    izando
    -1.63
    
    -1.59
     سانتی
    -1.58
     suplemento
    -1.57
    éges
    -1.53
    Ｔ
    -1.52
     question
    -1.51
    POSITIVE LOGITS
     the
    2.08
    ,
    1.73
     our
    1.55
     who
    1.44
     Therefore
    1.44
     Representatives
    1.37
    くれない
    1.34
    o
    1.34
     però
    1.32
    好きです
    1.32
    Activations Density 0.007%

    No Known Activations