© 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. 42840
    Prev
    Next
    INDEX
    Explanations

    origin and source

    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
     velours
    -1.48
    </i>
    -1.44
    _
    -1.41
    ઁ
    -1.40
    殍
    -1.38
     rente
    -1.36
     vitrine
    -1.36
     cabine
    -1.34
     enceinte
    -1.34
     balcon
    -1.31
    POSITIVE LOGITS
     from
    1.67
     öde
    1.52
    Leírás
    1.50
    翆
    1.41
    Alemania
    1.36
    вної
    1.34
    Ayy
    1.34
    赟
    1.34
     beträ
    1.33
     anahtar
    1.33
    Activations Density 0.096%

    No Known Activations