© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34856
    Prev
    Next
    INDEX
    Explanations

    critical points and transitions

    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
     largely
    -1.26
     predominantly
    -1.16
     저장
    -1.15
    有些人
    -1.09
     играет
    -1.04
     Tiefen
    -1.04
     heilig
    -1.03
     significantly
    -1.02
               
    -1.02
     costante
    -1.02
    POSITIVE LOGITS
     pasaba
    1.30
    tonsoft
    1.20
     there
    1.17
     ());
    1.16
    Leírás
    1.14
    Tó
    1.10
    ğan
    1.10
     hanya
    1.09
    時半
    1.09
    ֠
    1.06
    Activations Density 0.035%

    No Known Activations