© 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. 65747
    Prev
    Next
    INDEX
    Explanations

    citations markers

    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
    ↵↵
    -2.86
     zusätz
    -2.64
     offizi
    -2.61
    $
    -2.56
     präsenti
    -2.47
     touted
    -2.34
     varied
    -2.33
    .
    -2.30
     gewähr
    -2.28
    ل
    -2.28
    POSITIVE LOGITS
     ľudí
    2.55
    t
    2.42
    で
    2.30
    y
    2.25
    ſſen
    2.22
     наших
    2.19
     ใน
    2.17
     obyvateľov
    2.17
    य़
    2.16
    //
    2.09
    Activations Density 0.331%

    No Known Activations