© 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. 128679
    Prev
    Next
    INDEX
    Explanations

    state abbreviations

    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
    both
    -1.20
     нового
    -1.09
     formó
    -1.07
    Hechos
    -1.05
     .......
    -1.02
    Tämä
    -1.02
     acoged
    -1.01
     agradable
    -1.01
     ........
    -1.00
     dibutuhkan
    -0.99
    POSITIVE LOGITS
     with
    1.15
     meticulously
    1.05
     cleverly
    1.03
    )}$.
    1.02
     in
    1.02
    ÁR
    1.00
     after
    0.98
    金色
    0.98
     undeniably
    0.96
     does
    0.96
    Activations Density 0.003%

    No Known Activations