© 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. 22-GEMMASCOPE-RES-131K
    7. 13264
    Prev
    Next
    INDEX
    Explanations

    database identifiers and foreign keys

    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_22/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
    了什么
    -1.02
     all
    -0.99
     regista
    -0.98
     ensa
    -0.98
    ATEGORIES
    -0.96
    神奈川
    -0.96
    　　(
    -0.95
    presumably
    -0.91
     everything
    -0.91
    ılacak
    -0.91
    POSITIVE LOGITS
     from
    1.03
    曲を
    0.92
    άνει
    0.88
     поэтому
    0.87
     support
    0.85
    ueuse
    0.84
     NUT
    0.82
     därför
    0.81
    ָ
    0.80
     derfor
    0.79
    Activations Density 0.005%

    No Known Activations