© 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. 92503
    Prev
    Next
    INDEX
    Explanations

    social media effects

    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
    ^{[
    -0.85
    ('/',
    -0.80
    湿
    -0.77
    лении
    -0.75
     ding
    -0.75
    ﹗
    -0.74
    ينا
    -0.74
    tern
    -0.73
    DrawerLayout
    -0.73
     review
    -0.73
    POSITIVE LOGITS
     effects
    1.22
     Hov
    1.09
    Effects
    1.09
     Effects
    1.09
     message
    1.02
     messages
    0.99
     EFFECTS
    0.98
    effects
    0.97
     audience
    0.96
     publics
    0.92
    Activations Density 0.017%

    No Known Activations