© 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. 38115
    Prev
    Next
    INDEX
    Explanations

    code and concepts

    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
     lipca
    -0.75
     Proposals
    -0.75
    tigheter
    -0.73
     bakso
    -0.73
    тів
    -0.73
     Kontroll
    -0.69
     terminates
    -0.69
    Polish
    -0.69
     tendered
    -0.68
    pazität
    -0.67
    POSITIVE LOGITS
     Ato
    0.73
    ŭ
    0.73
     atro
    0.66
    Cb
    0.66
    を務
    0.62
     Ansari
    0.62
     veckan
    0.62
     Lagrange
    0.62
     મા
    0.61
    찍
    0.60
    Activations Density 0.028%

    No Known Activations