© 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. 10-GEMMASCOPE-RES-131K
    7. 127899
    Prev
    Next
    INDEX
    Explanations

    adjectives describing situations

    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_10/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
     atentos
    -1.54
    ᛬
    -1.35
    鹀
    -1.34
     servem
    -1.30
     BOMB
    -1.29
    ⽼
    -1.29
     jät
    -1.27
     anhänger
    -1.27
    __________
    -1.26
    Миха
    -1.26
    POSITIVE LOGITS
     would
    2.09
     you
    1.41
     won
    1.34
     didn
    1.30
    umbledore
    1.29
     couldn
    1.28
    ron
    1.27
     we
    1.27
     wouldn
    1.27
     could
    1.23
    Activations Density 0.010%

    No Known Activations