© 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. 68017
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    ︲
    -2.27
    呖
    -2.25
    AutoresizingMask
    -2.14
    鏷
    -1.92
    foreignKey
    -1.89
    းက
    -1.88
     diki
    -1.88
    ⇿
    -1.87
    
    -1.84
    ":"+
    -1.84
    POSITIVE LOGITS
    ed
    2.08
     able
    1.91
     considered
    1.87
    ان
    1.80
    '
    1.79
     termed
    1.79
    但她
    1.78
     imaged
    1.74
    ’
    1.73
    *
    1.73
    Activations Density 0.129%

    No Known Activations