© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57634
    Prev
    Next
    INDEX
    Explanations

    quantification and analysis qualifiers

    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
     microfilm
    -0.79
    GPA
    -0.77
     elk
    -0.71
     Producción
    -0.71
     GAO
    -0.70
     Clever
    -0.69
    ressive
    -0.69
    afterEach
    -0.68
     religieuses
    -0.68
    DateFormatter
    -0.68
    POSITIVE LOGITS
     flagged
    1.17
     flag
    1.07
    flag
    1.06
    censored
    1.02
     Flag
    1.02
     analyte
    0.94
     qualifiers
    0.90
     flags
    0.90
     quantit
    0.90
     qualified
    0.89
    Activations Density 0.003%

    No Known Activations