© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102069
    Prev
    Next
    INDEX
    Explanations

    delivery of services and results

    np_acts-logits-general · gemini-2.5-flash-lite

    delivering results or value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étend
    0.81
     extradition
    0.73
     Nhưng
    0.73
     authorizing
    0.70
     arrêt
    0.70
     schwierig
    0.70
     里
    0.68
     एकड़
    0.67
    ING
    0.66
    但不
    0.66
    POSITIVE LOGITS
    h
    0.88
    delivery
    0.86
    delivered
    0.86
     Delivering
    0.84
    deliver
    0.84
    1
    0.83
    交付
    0.80
    v
    0.80
     delivers
    0.79
     deliver
    0.79
    Activations Density 0.054%

    No Known Activations