© 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. 38157
    Prev
    Next
    INDEX
    Explanations

    arrest, remand, custody

    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
     hrá
    -0.91
     desconocido
    -0.86
     an
    -0.84
     testigo
    -0.82
     no
    -0.79
     there
    -0.79
     בד
    -0.77
     Characters
    -0.76
    クシー
    -0.76
    爭
    -0.75
    POSITIVE LOGITS
     remand
    1.28
     recovered
    1.19
     remanded
    1.18
     confessed
    1.08
     interrogation
    1.07
     arrested
    1.02
     arresting
    0.98
     confessions
    0.96
     arrest
    0.95
    Recover
    0.94
    Activations Density 0.017%

    No Known Activations