© 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. 109383
    Prev
    Next
    INDEX
    Explanations

    magic spells for creatures

    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
    čni
    -0.89
    过去了
    -0.82
    Axis
    -0.79
    Trinity
    -0.79
    Wilson
    -0.77
    Atomic
    -0.75
     警
    -0.74
    Сан
    -0.73
    田市
    -0.72
    Arduino
    -0.71
    POSITIVE LOGITS
     heroes
    1.04
     dwellings
    1.00
     rozwoju
    0.94
     spell
    0.91
     spells
    0.90
     creatures
    0.87
     hero
    0.84
     dispel
    0.84
     creature
    0.83
     DEI
    0.82
    Activations Density 0.019%

    No Known Activations