© 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. 2192
    Prev
    Next
    INDEX
    Explanations

    discrimination based on criteria

    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
     from
    -1.00
    期限
    -0.97
     significance
    -0.90
     Using
    -0.88
    שלום
    -0.87
     to
    -0.87
     excessively
    -0.84
    ما
    -0.82
    מא
    -0.81
     necessary
    -0.81
    POSITIVE LOGITS
     based
    1.66
     discrimination
    1.40
     Discrimination
    1.36
    discrimination
    1.27
    based
    1.24
     against
    1.23
     BASED
    1.20
    Based
    1.16
    experienced
    1.09
     hacia
    1.04
    Activations Density 0.026%

    No Known Activations