© 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. 21775
    Prev
    Next
    INDEX
    Explanations

    // Just testing

    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
    </em>
    -1.73
     zwi
    -1.67
     same
    -1.60
    𝑈
    -1.58
     redak
    -1.46
    ཥ
    -1.44
     gewi
    -1.41
     kulinar
    -1.38
     deklar
    -1.38
     frenos
    -1.38
    POSITIVE LOGITS
    4
    1.52
    ريكي
    1.47
     of
    1.40
     for
    1.39
     kematian
    1.31
    8
    1.31
     or
    1.30
     amidst
    1.27
    caneca
    1.27
     artful
    1.27
    Activations Density 0.166%

    No Known Activations