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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82417
    Prev
    Next
    INDEX
    Explanations

    US government agencies and reports

    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_34/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
    SEX
    -0.78
    zcze
    -0.78
    Ново
    -0.77
    敕
    -0.75
    Клуб
    -0.74
    jería
    -0.72
    Souza
    -0.72
    uoš
    -0.71
    чить
    -0.71
    kval
    -0.71
    POSITIVE LOGITS
     GAO
    2.08
    GA
    1.63
     General
    1.42
    gao
    1.37
     Congressional
    1.26
     Government
    1.23
     Accountability
    1.23
     GA
    1.16
    General
    1.11
     RAND
    1.11
    Activations Density 0.061%

    No Known Activations