© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115945
    Prev
    Next
    INDEX
    Explanations

    X-Men and code commands

    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
    crip
    -0.79
     Pump
    -0.76
    eterminate
    -0.76
     venting
    -0.75
     Griffith
    -0.74
    átil
    -0.74
     Worcester
    -0.74
    uttaa
    -0.74
     Bristol
    -0.71
    ГЛА
    -0.71
    POSITIVE LOGITS
     mutant
    1.44
     mutants
    1.44
     X
    1.34
    mutant
    1.31
    Mutant
    1.30
     Mutant
    1.22
     Magneto
    1.22
     Xavier
    1.14
    Magne
    1.13
     Wolverine
    1.06
    Activations Density 0.033%

    No Known Activations