© 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. 54018
    Prev
    Next
    INDEX
    Explanations

    section markers like b), II., B

    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
     exceedingly
    -0.98
    錆
    -0.96
    正しい
    -0.95
    靚
    -0.90
     totalité
    -0.90
     qualsiasi
    -0.88
     ausreich
    -0.87
     encantador
    -0.87
     financieros
    -0.86
     hason
    -0.86
    POSITIVE LOGITS
     Other
    1.45
     other
    1.26
     How
    1.21
     What
    1.20
    Other
    1.15
    其他
    1.14
    other
    1.11
     Does
    1.11
     سایر
    1.09
     what
    1.05
    Activations Density 0.019%

    No Known Activations