© 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. 21881
    Prev
    Next
    INDEX
    Explanations

    switch statement

    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
     is
    -1.87
     because
    -1.72
    任何
    -1.62
     was
    -1.59
     by
    -1.56
     and
    -1.53
     would
    -1.49
     any
    -1.47
    )
    -1.38
    了他的
    -1.38
    POSITIVE LOGITS
     that
    1.70
     niektor
    1.54
     制服
    1.43
     ludzie
    1.41
    tivazione
    1.40
    Миха
    1.36
    albeit
    1.31
    Zdroj
    1.31
     jednu
    1.31
     aparentemente
    1.30
    Activations Density 0.007%

    No Known Activations