© 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. 110808
    Prev
    Next
    INDEX
    Explanations

    first words of sentences

    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
    ücksich
    -0.77
    iserie
    -0.75
     afterwards
    -0.68
     Hangzhou
    -0.66
     tallied
    -0.65
     diversité
    -0.65
    Características
    -0.65
    Casi
    -0.65
     Spitz
    -0.65
     Getter
    -0.65
    POSITIVE LOGITS
     Age
    0.90
    Age
    0.83
     Baxter
    0.78
     diff
    0.75
     беже
    0.75
     lingü
    0.74
     Supervision
    0.74
     Kemp
    0.73
     信
    0.72
    value
    0.71
    Activations Density 0.019%

    No Known Activations