© 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. 280
    Prev
    Next
    INDEX
    Explanations

    speaks on or about

    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
     either
    -1.40
     both
    -1.30
     mindestens
    -1.21
     Either
    -1.20
     it
    -1.19
    不管是
    -1.18
     Eigentü
    -1.17
    It
    -1.13
     there
    -1.13
    Either
    -1.11
    POSITIVE LOGITS
     gani
    1.39
     kampen
    1.38
     nabi
    1.37
    ߋ
    1.35
     egens
    1.27
     klima
    1.26
    
    1.26
     how
    1.23
     nivå
    1.22
     egent
    1.22
    Activations Density 0.076%

    No Known Activations