© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77191
    Prev
    Next
    INDEX
    Explanations

    adjectives preceding nouns

    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
     inni
    -0.99
     Londra
    -0.98
     moteurs
    -0.95
    ிரு
    -0.94
     rej
    -0.91
    ších
    -0.91
     kaffe
    -0.90
     truk
    -0.90
    Após
    -0.90
     brome
    -0.90
    POSITIVE LOGITS
     Different
    1.08
    different
    1.01
     Change
    0.94
     to
    0.94
    point
    0.94
     Certain
    0.93
     Known
    0.93
    jako
    0.90
    那你
    0.89
    ,
    0.88
    Activations Density 0.077%

    No Known Activations