© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70245
    Prev
    Next
    INDEX
    Explanations

    when followed by 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
    。
    -1.62
    eload
    -1.62
    镲
    -1.55
     dát
    -1.48
    ଃ
    -1.47
    cising
    -1.45
    atized
    -1.40
     who
    -1.39
    .");
    -1.38
    atization
    -1.38
    POSITIVE LOGITS
     this
    1.44
     Initially
    1.41
     after
    1.38
    いいのか
    1.38
     I
    1.38
     in
    1.37
    ?
    1.34
     initially
    1.31
     time
    1.27
    ↵↵↵
    1.25
    Activations Density 0.061%

    No Known Activations