© 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. 75537
    Prev
    Next
    INDEX
    Explanations

    scientific analysis and grids

    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
    ור
    -0.83
    ária
    -0.81
    тель
    -0.75
    nthetic
    -0.75
    Speech
    -0.73
    rawDesc
    -0.71
    ácie
    -0.71
     flirting
    -0.69
    faqs
    -0.69
    ALU
    -0.68
    POSITIVE LOGITS
     Grid
    1.50
    Grid
    1.38
     grid
    1.35
    grid
    1.24
     scientific
    1.09
    GRID
    1.08
     Glo
    1.07
     Scientific
    1.05
     middleware
    1.05
     scientists
    0.99
    Activations Density 0.111%

    No Known Activations