© 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. 102488
    Prev
    Next
    INDEX
    Explanations

    police and sheriff departments

    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
    actéristiques
    -0.80
    Preconditions
    -0.78
     причине
    -0.75
    Constructor
    -0.75
    脆
    -0.74
    icznego
    -0.74
    jutan
    -0.73
     каз
    -0.73
     ἄ
    -0.73
     CAG
    -0.73
    POSITIVE LOGITS
     police
    3.03
     Police
    2.36
    Police
    2.03
    police
    1.86
     sheriff
    1.73
     POLICE
    1.59
     Sheriff
    1.54
     Polizei
    1.52
     पुलिस
    1.45
     NYPD
    1.45
    Activations Density 0.082%

    No Known Activations