© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116774
    Prev
    Next
    INDEX
    Explanations

    i was + past action or state

    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
    thodoxy
    -1.48
     now
    -1.39
    ̀
    -1.25
    ícias
    -1.22
    ेशा
    -1.17
    现在
    -1.17
     derzeit
    -1.11
    imetry
    -1.10
    formatie
    -1.10
     auteurs
    -1.10
    POSITIVE LOGITS
     hoping
    1.80
     able
    1.79
     expecting
    1.55
     thinking
    1.53
     told
    1.45
     originally
    1.45
     wondering
    1.32
     recently
    1.28
     born
    1.21
     autrefois
    1.19
    Activations Density 0.040%

    No Known Activations