© 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. 116677
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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
    ēs
    -0.82
    ⊖
    -0.81
     Chandigarh
    -0.80
     TEXAS
    -0.79
    önster
    -0.78
    ädie
    -0.78
     viande
    -0.78
     Synonyms
    -0.77
     lò
    -0.76
     miejsca
    -0.75
    POSITIVE LOGITS
     Maryland
    1.21
    Maryland
    1.03
     Potomac
    0.96
    appspot
    0.89
     река
    0.87
    гают
    0.85
    Temporada
    0.84
     nécessairement
    0.82
     Baltimore
    0.81
    More
    0.81
    Activations Density 0.017%

    No Known Activations