© 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. 11153
    Prev
    Next
    INDEX
    Explanations

    question phrases and statements

    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
    V
    -1.30
     damaligen
    -1.23
     zahlreichen
    -1.20
    r
    -1.20
     ול
    -1.19
     griechischen
    -1.19
    W
    -1.18
    rightarrow
    -1.17
     pelig
    -1.16
    、
    -1.15
    POSITIVE LOGITS
    ність
    1.33
    ierend
    1.30
     vinden
    1.26
    Dang
    1.25
    æng
    1.23
    lorn
    1.22
     zaragoza
    1.22
    ными
    1.20
    hanced
    1.17
     etui
    1.17
    Activations Density 0.093%

    No Known Activations