© 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. 90841
    Prev
    Next
    INDEX
    Explanations

    free software

    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
     there
    -1.03
     this
    -0.98
    there
    -0.86
     at
    -0.84
     it
    -0.82
    だそうです
    -0.78
     maravilla
    -0.75
     showcasing
    -0.74
    ajuku
    -0.74
     miejsce
    -0.72
    POSITIVE LOGITS
    Its
    1.05
    ogs
    0.92
     its
    0.92
    ypes
    0.90
    вия
    0.88
    rof
    0.87
    itself
    0.86
    뺨
    0.85
     EAT
    0.85
    Blanc
    0.84
    Activations Density 0.112%

    No Known Activations