© 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. 103820
    Prev
    Next
    INDEX
    Explanations

    constructed fantasy Construct

    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
    ivil
    -0.76
     Terrorism
    -0.72
     resilient
    -0.72
     Foul
    -0.69
    Oste
    -0.68
     قابلیت
    -0.68
     Hola
    -0.67
     Corruption
    -0.66
     palacio
    -0.66
     coches
    -0.66
    POSITIVE LOGITS
     fantasy
    1.09
     constructed
    1.08
    constructed
    0.97
    Constructed
    0.97
    Fantasy
    0.94
     Constructed
    0.90
     konstru
    0.88
     Magic
    0.81
     Wizards
    0.81
     Clarke
    0.80
    Activations Density 0.033%

    No Known Activations