© 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. 33802
    Prev
    Next
    INDEX
    Explanations

    subjective experiences and evaluations

    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
     umożli
    -1.17
     olvidado
    -1.13
    くれ
    -1.07
    告诉我
    -1.05
     ajutor
    -1.05
     nimic
    -1.03
    走吧
    -1.02
     acesta
    -0.99
     znajd
    -0.98
     aislado
    -0.97
    POSITIVE LOGITS
     to
    3.89
     having
    2.53
     seeing
    2.34
     being
    2.20
     that
    2.13
    having
    1.98
     hearing
    1.77
     getting
    1.64
     watching
    1.63
     how
    1.58
    Activations Density 0.065%

    No Known Activations