© 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. 33139
    Prev
    Next
    INDEX
    Explanations

    array programming constructs

    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
     garrafa
    -0.85
     nevera
    -0.82
    CROSSTALK
    -0.81
     treno
    -0.80
     normalement
    -0.80
     aparelho
    -0.80
     tertulis
    -0.79
    文分享
    -0.77
     جست
    -0.77
    uples
    -0.76
    POSITIVE LOGITS
    seus
    0.88
     AR
    0.85
     Ar
    0.81
    Afficher
    0.75
    BlockingQueue
    0.74
     скоро
    0.73
    THINK
    0.72
     sudo
    0.71
    lie
    0.69
     всему
    0.69
    Activations Density 0.012%

    No Known Activations