© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64555
    Prev
    Next
    INDEX
    Explanations

    cost, money, and resources

    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
     block
    -0.80
    block
    -0.78
     immune
    -0.77
     НИ
    -0.75
     tentang
    -0.73
    ogens
    -0.73
     forsø
    -0.72
    ajikan
    -0.71
     BLOCK
    -0.71
     prob
    -0.71
    POSITIVE LOGITS
     mana
    1.16
     colorless
    1.05
     cost
    1.00
     colourless
    0.97
     energy
    0.94
    mana
    0.84
     sons
    0.80
    cost
    0.80
     costs
    0.78
    Mana
    0.78
    Activations Density 0.007%

    No Known Activations