© 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. 111015
    Prev
    Next
    INDEX
    Explanations

    receiving

    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
    y
    -1.49
    :
    -1.46
    x
    -1.33
    3
    -1.30
     الرابع
    -1.29
    是否
    -1.25
    鵝
    -1.23
    +
    -1.20
    Should
    -1.20
     environ
    -1.20
    POSITIVE LOGITS
    跸
    1.29
    produksi
    1.25
     rompi
    1.23
     récentes
    1.23
     from
    1.22
    lardan
    1.22
    ENCIL
    1.22
     donnent
    1.20
     únicamente
    1.20
    čni
    1.20
    Activations Density 0.234%

    No Known Activations