© 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. 42505
    Prev
    Next
    INDEX
    Explanations

    explaining 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
    })^
    -1.43
    "]["
    -1.32
     preguntó
    -1.30
    笮
    -1.27
    ibilité
    -1.22
     vinyle
    -1.20
    lijke
    -1.18
    cians
    -1.16
    $};
    -1.13
    liners
    -1.11
    POSITIVE LOGITS
     when
    1.93
     where
    1.49
     it
    1.35
     своего
    1.31
     its
    1.30
     suele
    1.23
    它的
    1.23
     Их
    1.23
     things
    1.23
     cuando
    1.22
    Activations Density 0.087%

    No Known Activations