© 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. 883
    Prev
    Next
    INDEX
    Explanations

    This is a

    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
     semblent
    -1.29
    berikut
    -1.26
     Unterkunft
    -1.23
     Lieferung
    -1.21
     Präsidenten
    -1.20
    sätzlich
    -1.19
     autén
    -1.18
    蒞
    -1.17
    epam
    -1.17
    ministerium
    -1.17
    POSITIVE LOGITS
     this
    1.68
    when
    1.52
     iload
    1.48
     fortfarande
    1.46
     you
    1.46
     alamy
    1.42
    vantaged
    1.42
    The
    1.42
    This
    1.41
     SqlConnection
    1.41
    Activations Density 0.012%

    No Known Activations