© 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. 10-GEMMASCOPE-RES-131K
    7. 120137
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    la
    -1.53
    u
    -1.49
    g
    -1.40
    na
    -1.38
    an
    -1.34
    ad
    -1.33
    od
    -1.28
    ing
    -1.27
    ca
    -1.25
    ile
    -1.24
    POSITIVE LOGITS
     regionale
    1.12
     tussen
    1.12
     všech
    1.11
     territoires
    1.11
     utilisé
    1.11
    bluza
    1.09
    stans
    1.09
     második
    1.08
     montagnes
    1.08
    縋
    1.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.