© 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. 54272
    Prev
    Next
    INDEX
    Explanations

    trolley roll droid doll

    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
    lossians
    -0.78
     complejo
    -0.76
     see
    -0.75
     Looks
    -0.73
     سرد
    -0.71
     查
    -0.71
     OBE
    -0.68
    امل
    -0.68
    tigos
    -0.67
    Complexity
    -0.67
    POSITIVE LOGITS
     troll
    1.64
     Troll
    1.53
     trolls
    1.33
     trol
    1.18
    Troll
    1.13
    troll
    1.11
    olol
    1.07
     trolling
    1.01
    yAxis
    0.87
     Gruber
    0.87
    Activations Density 0.027%

    No Known Activations