© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62556
    Prev
    Next
    INDEX
    Explanations

    casting spells

    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
    Negative Logits
     prosec
    -0.84
    vedades
    -0.78
    рил
    -0.76
    Ski
    -0.75
    practice
    -0.75
    apos
    -0.75
    Practice
    -0.74
    DUN
    -0.74
     detta
    -0.74
    Publications
    -0.73
    POSITIVE LOGITS
     spell
    1.70
     spells
    1.66
     fireball
    1.15
    spells
    1.15
    spell
    1.14
     Spell
    1.02
     Spells
    0.99
     illusion
    0.99
    Spell
    0.97
     magic
    0.96
    Activations Density 0.011%

    No Known Activations