© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116747
    Prev
    Next
    INDEX
    Explanations

    past tense actions after "he"

    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_34/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
     yesterday
    -1.39
     сегодня
    -1.26
     сейчас
    -1.22
     vergangenen
    -1.20
     some
    -1.19
     tonight
    -1.17
     today
    -1.13
     gestern
    -1.13
     früheren
    -1.13
     zuletzt
    -1.05
    POSITIVE LOGITS
     again
    1.24
    "/",
    1.16
    再次
    1.16
     ciebie
    1.12
    ]],
    1.09
    again
    1.07
     echter
    1.05
    ֔
    1.05
     patrie
    1.04
    ]</
    1.03
    Activations Density 0.180%

    No Known Activations