© 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. 82890
    Prev
    Next
    INDEX
    Explanations

    criminal reports and complaints

    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
    ané
    -0.85
    ガーデン
    -0.84
     probed
    -0.84
    新华
    -0.84
    גות
    -0.81
    Zag
    -0.81
     condolence
    -0.80
    overset
    -0.79
     Peat
    -0.78
     IMDG
    -0.76
    POSITIVE LOGITS
     filing
    2.34
     filed
    2.22
     report
    2.17
     reporting
    2.13
     reported
    1.81
    Filing
    1.80
    report
    1.77
     Report
    1.77
    Report
    1.75
     file
    1.73
    Activations Density 0.021%

    No Known Activations