© 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. 10-GEMMASCOPE-RES-131K
    7. 9376
    Prev
    Next
    INDEX
    Explanations

    activities and states

    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_10/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
     BOTH
    -1.19
     namn
    -1.12
     केवल
    -1.11
     sogar
    -1.11
    テト
    -1.10
     كافة
    -1.09
    📏
    -1.09
     pão
    -1.09
    einer
    -1.09
    //:
    -1.08
    POSITIVE LOGITS
     further
    1.34
     or
    1.25
    Builders
    1.20
     schwarze
    1.09
     from
    1.09
     zawsze
    1.05
     if
    1.02
    mouthed
    1.02
     rekomendasi
    1.00
    办法
    1.00
    Activations Density 0.114%

    No Known Activations