© 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. 22-GEMMASCOPE-RES-131K
    7. 79946
    Prev
    Next
    INDEX
    Explanations

    XML tags and code structures

    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_22/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
     feront
    -1.14
    ць
    -1.14
    umers
    -1.10
     debacle
    -1.06
    exercice
    -1.03
     visi
    -1.00
    neous
    -1.00
     valentin
    -0.99
     andreas
    -0.99
     chanteur
    -0.98
    POSITIVE LOGITS
    まじ
    1.20
     kämpfen
    1.16
     limpi
    1.15
    にします
    1.15
     tedy
    1.10
    ustomed
    1.09
     kumaş
    1.09
     thâm
    1.08
    racked
    1.07
    将来
    1.03
    Activations Density 0.000%

    No Known Activations