© 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. 10-GEMMASCOPE-RES-131K
    7. 105035
    Prev
    Next
    INDEX
    Explanations

    note that

    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
    TokenNameDOT
    -1.43
    的所有
    -1.38
     室内
    -1.38
     мяг
    -1.33
     Where
    -1.32
     способ
    -1.30
    だよ
    -1.29
    leys
    -1.29
     Also
    -1.27
    Champaign
    -1.23
    POSITIVE LOGITS
     that
    3.16
    although
    1.78
    albeit
    1.67
     saati
    1.57
    despite
    1.55
     julk
    1.55
    身后的
    1.52
     viime
    1.51
    řej
    1.50
     qed
    1.49
    Activations Density 0.016%

    No Known Activations