© 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. 22-GEMMASCOPE-RES-131K
    7. 65009
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Both
    -1.33
     Siapa
    -1.29
    
    -1.27
    ''',
    -1.25
     овощи
    -1.24
    Asthma
    -1.19
     herido
    -1.19
     אנחנו
    -1.18
    Veranstal
    -1.16
    awarkan
    -1.15
    POSITIVE LOGITS
     drenched
    1.66
     disregarding
    1.46
     abnormally
    1.40
     persuading
    1.36
    ּוֹ
    1.34
    ַּ
    1.33
     delineated
    1.32
    感じが
    1.30
    ִּ
    1.30
     contradictory
    1.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.