© 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. 65957
    Prev
    Next
    INDEX
    Explanations

    full class or identifier names

    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
    mited
    -0.82
    Vlastnosti
    -0.78
     płasz
    -0.77
    Dedicated
    -0.77
    FileSize
    -0.76
    FEATURES
    -0.75
    ihnach
    -0.75
    甩
    -0.74
    rapport
    -0.73
    Lying
    -0.73
    POSITIVE LOGITS
     references
    1.49
     identification
    1.38
     name
    1.29
     referencing
    1.27
     reference
    1.25
     names
    1.25
     referencias
    1.22
     identifier
    1.19
     identifiers
    1.17
    URI
    1.16
    Activations Density 0.049%

    No Known Activations