© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26616
    Prev
    Next
    INDEX
    Explanations

    endings like ing or ering

    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
     certainly
    -1.35
     other
    -1.29
     these
    -1.24
    достатки
    -1.24
     both
    -1.16
     should
    -1.15
     distinctly
    -1.14
     adequate
    -1.12
     perhaps
    -1.12
     this
    -1.12
    POSITIVE LOGITS
     familières
    1.20
     travaillent
    1.20
    детская
    1.18
     télécharger
    1.17
     brasileiros
    1.17
     publice
    1.16
    ѝ
    1.13
    ᾽
    1.13
     พร้อม
    1.11
    детский
    1.11
    Activations Density 0.141%

    No Known Activations