© 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. 116736
    Prev
    Next
    INDEX
    Explanations

    tournament entry and rules

    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
    %%%%%%%%%%
    -0.95
    Visits
    -0.90
    STEP
    -0.86
    पाद
    -0.85
    INK
    -0.85
     Nutzer
    -0.85
    hani
    -0.84
    Weekly
    -0.82
     Internship
    -0.81
     InkWell
    -0.80
    POSITIVE LOGITS
     entries
    1.54
     registration
    1.52
     officials
    1.30
     competitors
    1.20
     judges
    1.20
     rules
    1.18
     entry
    1.16
     protest
    1.15
    entries
    1.14
     entrants
    1.14
    Activations Density 0.030%

    No Known Activations