© 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. 115685
    Prev
    Next
    INDEX
    Explanations

    stumble upon or across

    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
     sharply
    -1.00
     berada
    -0.87
     respirar
    -0.81
    '
    -0.81
     veramente
    -0.81
     Outcome
    -0.80
    قامت
    -0.80
     careful
    -0.79
     vuole
    -0.79
     fabulous
    -0.79
    POSITIVE LOGITS
     stumbling
    1.08
     bumble
    1.05
     tumble
    1.04
     fumble
    1.02
     stumbled
    0.99
     stumble
    0.99
    umble
    0.97
    umbles
    0.90
    umbling
    0.89
    BlockSize
    0.89
    Activations Density 0.010%

    No Known Activations