© 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. 12284
    Prev
    Next
    INDEX
    Explanations

    authoritarian regime dictatorship

    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
    ings
    -1.25
    (!__
    -1.16
     diversos
    -1.16
    ᧐
    -1.13
    래스
    -1.13
    िंग
    -1.11
    ԝ
    -1.11
     crucial
    -1.11
    ,«
    -1.11
    っていました
    -1.10
    POSITIVE LOGITS
    ↵
    1.35
     regime
    1.19
     control
    1.18
     regimes
    1.12
     while
    1.06
     if
    1.06
     systemu
    1.05
     rež
    1.02
     esperamos
    1.02
    出来ました
    1.01
    Activations Density 0.022%

    No Known Activations