© 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. 60017
    Prev
    Next
    INDEX
    Explanations

    you 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_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
     overtaken
    -1.46
     होती
    -1.33
     arisen
    -1.20
    yordu
    -1.17
     stolen
    -1.16
    と言われる
    -1.16
     risen
    -1.14
    thrown
    -1.11
    stolen
    -1.05
     Starts
    -1.05
    POSITIVE LOGITS
     took
    1.87
     did
    1.74
     gave
    1.63
     went
    1.60
     got
    1.55
     threw
    1.55
     performed
    1.38
     está
    1.31
     drew
    1.30
     made
    1.29
    Activations Density 0.310%

    No Known Activations