© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1869
    Prev
    Next
    INDEX
    Explanations

    compound phrases and collocations

    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
    contexts
    -1.00
    Cases
    -0.95
    Contexts
    -0.95
     eras
    -0.90
     faç
    -0.90
     einzelnen
    -0.90
     Situations
    -0.89
     algunos
    -0.89
     mascar
    -0.89
     environments
    -0.88
    POSITIVE LOGITS
     these
    1.20
     mga
    1.06
     pair
    1.05
    一对
    0.99
    these
    0.97
    ские
    0.93
     THESE
    0.92
    These
    0.91
    pair
    0.90
     those
    0.88
    Activations Density 0.257%

    No Known Activations