© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98377
    Prev
    Next
    INDEX
    Explanations

    static, serializable, virtual

    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
     emigrants
    -0.84
    쿠
    -0.80
     додат
    -0.79
    걷
    -0.77
    Mald
    -0.77
     質
    -0.75
    vedì
    -0.75
     invoices
    -0.74
     Physic
    -0.74
     billiard
    -0.74
    POSITIVE LOGITS
    buyers
    0.93
    both
    0.92
    锃
    0.91
    .}(
    0.90
    ♙
    0.89
     fofo
    0.88
    itory
    0.88
    aing
    0.87
    dial
    0.85
    chea
    0.85
    Activations Density 0.002%

    No Known Activations