© 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. 34-GEMMASCOPE-RES-131K
    7. 116584
    Prev
    Next
    INDEX
    Explanations

    copyright notices and years

    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_34/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
     Travellers
    -0.82
    +%
    -0.80
     Bangor
    -0.79
    バイオ
    -0.76
    recip
    -0.76
    ortho
    -0.75
     RISERVATA
    -0.75
     nochmal
    -0.75
     emit
    -0.73
     tacto
    -0.73
    POSITIVE LOGITS
    したのが
    0.90
     télévisée
    0.84
     ấm
    0.83
     apologies
    0.81
    ARIO
    0.79
     Layer
    0.76
    undheit
    0.76
     väč
    0.76
    ebenarnya
    0.75
    膳
    0.75
    Activations Density 0.227%

    No Known Activations