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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93503
    Prev
    Next
    INDEX
    Explanations

    legal investigations and prosecutors

    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
     Policy
    -0.79
    政策
    -0.78
    POLICY
    -0.75
     блюда
    -0.75
    policy
    -0.74
     policy
    -0.73
    Policy
    -0.72
    Analytic
    -0.72
    Preface
    -0.71
    🤭
    -0.71
    POSITIVE LOGITS
     investigating
    1.58
     prosecutors
    1.48
     investigation
    1.47
     prosecutor
    1.42
     investigations
    1.41
    Prosecutors
    1.30
     indict
    1.25
     investigate
    1.24
     investigators
    1.24
    investig
    1.19
    Activations Density 0.026%

    No Known Activations