© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64932
    Prev
    Next
    INDEX
    Explanations

    legal counsel and prosecution titles

    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
    ㄑ
    -0.80
    バース
    -0.74
     breadcrumbs
    -0.72
     Literacy
    -0.71
    chila
    -0.71
    felder
    -0.70
     sida
    -0.70
    FCM
    -0.70
     grå
    -0.69
     rainwater
    -0.69
    POSITIVE LOGITS
     prosecuting
    1.11
     prosecution
    0.99
     DPP
    0.98
     decision
    0.96
     prosecute
    0.95
     prosecutors
    0.94
    Prosecutors
    0.92
     file
    0.91
     prosecutions
    0.91
     prosecuted
    0.90
    Activations Density 0.053%

    No Known Activations