© 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. 62997
    Prev
    Next
    INDEX
    Explanations

    bonuses and incentives

    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
    ậy
    -0.98
    供給
    -0.84
    afford
    -0.81
    affordable
    -0.81
     afford
    -0.80
    ailangan
    -0.75
    JsonValue
    -0.74
    ヌード
    -0.73
     Artillery
    -0.73
    ributes
    -0.73
    POSITIVE LOGITS
     bonus
    4.31
     bonuses
    3.95
    bonus
    3.25
     Bonus
    3.16
    Bonus
    3.09
     Bonuses
    2.73
    Bonuses
    2.52
     incentive
    2.33
     BONUS
    2.17
    BONUS
    2.08
    Activations Density 0.034%

    No Known Activations