© 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. 6771
    Prev
    Next
    INDEX
    Explanations

    facebook pages, groups, feed

    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
    bilecek
    -0.99
     auspicious
    -0.98
     также
    -0.93
     terrific
    -0.90
     magnificent
    -0.90
    Tarih
    -0.88
    ApiProperty
    -0.88
     discard
    -0.85
     unforgettable
    -0.84
    </b>
    -0.84
    POSITIVE LOGITS
     Messenger
    1.38
     page
    1.32
     messenger
    1.30
     pages
    1.11
     groups
    1.11
    Facebook
    1.09
    groups
    1.09
     GROUPS
    1.08
     POSTS
    1.07
     fb
    1.05
    Activations Density 0.011%

    No Known Activations