© 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. 22-GEMMASCOPE-RES-131K
    7. 72684
    Prev
    Next
    INDEX
    Explanations

    describes subsequent specific noun

    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_22/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
     MAKES
    -1.59
    ’
    -1.57
    なども
    -1.56
     Boletín
    -1.49
    alers
    -1.42
    opie
    -1.39
    
    -1.39
    inerary
    -1.38
    킁
    -1.37
    
    -1.34
    POSITIVE LOGITS
    <b>
    1.29
    <strong>
    1.27
    Comté
    1.23
     dengan
    1.20
     This
    1.19
    "
    1.19
    地产
    1.16
    ↵
    1.14
     Each
    1.14
     provides
    1.13
    Activations Density 5.744%

    No Known Activations