© 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. 33506
    Prev
    Next
    INDEX
    Explanations

    creating/updating database fields

    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
     tỏi
    -0.85
     później
    -0.81
     folgender
    -0.79
     bekannten
    -0.79
    robert
    -0.78
     关于
    -0.78
    何度
    -0.76
    ragan
    -0.76
     ocasião
    -0.75
    keith
    -0.75
    POSITIVE LOGITS
     Fields
    1.02
    oredCriteria
    1.02
     Columns
    1.00
    Fields
    0.96
    UnknownFields
    0.90
    JTextField
    0.90
    Columns
    0.88
    컬
    0.86
    writeByte
    0.85
     fields
    0.85
    Activations Density 0.060%

    No Known Activations