© 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. 109300
    Prev
    Next
    INDEX
    Explanations

    after school his

    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
    announced
    -1.25
     clôture
    -1.23
     nôtre
    -1.22
    began
    -1.20
    wants
    -1.20
    つづく
    -1.17
    сумка
    -1.17
    婼
    -1.13
    became
    -1.13
     Vielzahl
    -1.12
    POSITIVE LOGITS
     he
    1.34
     him
    1.32
     Mr
    1.31
    2
    1.26
     his
    1.24
    1
    1.22
    車は
    1.15
     mr
    1.09
     apparently
    1.08
     zwier
    1.06
    Activations Density 0.414%

    No Known Activations