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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11524
    Prev
    Next
    INDEX
    Explanations

    government and legislators

    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
    ☽
    -1.33
     веществ
    -1.17
     печени
    -1.14
     familien
    -1.12
    wohner
    -1.11
     الده
    -1.11
     گیاه
    -1.09
    YEAR
    -1.09
    леп
    -1.07
    się
    -1.05
    POSITIVE LOGITS
     strategy
    1.52
     przód
    1.48
     vorbereitet
    1.38
    IKit
    1.34
     oignon
    1.31
     remaining
    1.29
    ּוֹ
    1.27
     embreagem
    1.27
    ִּ
    1.25
    נחנו
    1.25
    Activations Density 0.050%

    No Known Activations