© 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. 34-GEMMASCOPE-RES-131K
    7. 103544
    Prev
    Next
    INDEX
    Explanations

    sentence terminator

    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_34/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
     mereka
    -1.14
     België
    -1.11
    窸
    -1.10
     endi
    -1.07
     fhould
    -1.05
     ftill
    -1.02
     erd
    -1.02
     feveral
    -1.01
     pecuni
    -0.99
     atof
    -0.97
    POSITIVE LOGITS
     our
    2.27
     when
    1.86
     we
    1.83
     it
    1.52
    When
    1.48
    Often
    1.35
     When
    1.29
     Often
    1.28
     instead
    1.28
     naše
    1.26
    Activations Density 0.042%

    No Known Activations