© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108065
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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
     varied
    -0.95
     Sobald
    -0.90
     carattere
    -0.87
    七年
    -0.84
     its
    -0.84
     includes
    -0.84
     [];
    -0.83
    าม
    -0.83
    ={[
    -0.82
    chê
    -0.81
    POSITIVE LOGITS
     =
    1.07
     montre
    0.96
     marchand
    0.91
     lópez
    0.87
    )=$
    0.86
    攥
    0.85
     citar
    0.85
     Neve
    0.84
     garante
    0.84
     objectif
    0.84
    Activations Density 0.059%

    No Known Activations