© 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. 82389
    Prev
    Next
    INDEX
    Explanations

    license version later

    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
     процес
    -0.75
    唱歌
    -0.73
     échelle
    -0.72
     procédure
    -0.72
    などを
    -0.72
     яго
    -0.69
     искусство
    -0.68
     パーツ
    -0.68
     permasalahan
    -0.67
    駅から
    -0.67
    POSITIVE LOGITS
     spost
    0.88
     comprenant
    0.85
     REPLACE
    0.84
     ostat
    0.82
    voyer
    0.81
     KU
    0.81
     specif
    0.80
    CLUD
    0.80
     vider
    0.79
    roveň
    0.78
    Activations Density 0.314%

    No Known Activations