© 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. 103916
    Prev
    Next
    INDEX
    Explanations

    programming keywords and APIs

    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
     particuli
    -0.99
     yere
    -0.94
     particular
    -0.93
    particularly
    -0.93
     seksi
    -0.92
     particulier
    -0.92
     sitt
    -0.90
     varier
    -0.90
     particularmente
    -0.88
     PARTICULAR
    -0.88
    POSITIVE LOGITS
     {
    1.45
     {
    1.23
     with
    1.11
    ("${
    1.09
     же
    0.95
     también
    0.94
     as
    0.93
    OrNull
    0.93
     však
    0.93
     if
    0.93
    Activations Density 0.008%

    No Known Activations