© 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. 102013
    Prev
    Next
    INDEX
    Explanations

    explains why

    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
     not
    -2.25
     with
    -2.11
     different
    -1.63
     especially
    -1.44
     through
    -1.38
     while
    -1.38
     without
    -1.35
     all
    -1.30
     even
    -1.24
     in
    -1.23
    POSITIVE LOGITS
     fijn
    1.46
     vandaag
    1.45
    }
    1.41
     anymore
    1.36
     nor
    1.36
     или
    1.35
     bây
    1.34
    或
    1.34
     temperatuur
    1.31
     who
    1.30
    Activations Density 0.085%

    No Known Activations