© 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. 39669
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases often followed by a specific token

    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
     "
    -1.70
     is
    -1.68
    "
    -1.65
    ?"
    -1.60
     '
    -1.53
    ？」
    -1.53
     
    -1.53
     provide
    -1.42
     "...
    -1.42
    “
    -1.41
    POSITIVE LOGITS
    ᒍ
    1.86
    盉
    1.80
     tässä
    1.70
    
    1.67
     siinä
    1.67
    蚡
    1.62
     fonctionner
    1.61
     gewi
    1.59
    žiť
    1.59
    禵
    1.59
    Activations Density 0.018%

    No Known Activations