© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34972
    Prev
    Next
    INDEX
    Explanations

    Pokemon trainer items

    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
    氅
    -0.84
    腋
    -0.81
    exercice
    -0.74
    bullet
    -0.74
    Espace
    -0.74
     ">=
    -0.73
     exécut
    -0.73
     английском
    -0.73
    ystick
    -0.73
     Châ
    -0.72
    POSITIVE LOGITS
     team
    1.31
     trainer
    1.22
     battle
    1.16
     teams
    1.05
     battling
    1.03
    team
    0.98
     Trainer
    0.98
     battled
    0.97
     weakened
    0.97
     species
    0.93
    Activations Density 0.009%

    No Known Activations