© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78843
    Prev
    Next
    INDEX
    Explanations

    mage or wizard

    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
     Mache
    -0.84
     מוש
    -0.83
    💉
    -0.73
     Goliath
    -0.73
    Awards
    -0.71
     желез
    -0.71
     Perla
    -0.71
     عک
    -0.71
     bacterial
    -0.70
     파일
    -0.69
    POSITIVE LOGITS
     wizard
    2.19
     spells
    2.06
     spell
    2.03
     wizards
    2.02
     mage
    1.84
     magician
    1.83
     Wizard
    1.82
    Wizard
    1.80
     Wizards
    1.80
     magic
    1.78
    Activations Density 0.048%

    No Known Activations