© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11730
    Prev
    Next
    INDEX
    Explanations

    saving money and reducing costs

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

    minimize, reduce, efficient

    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
    的感觉
    0.50
     tarixi
    0.46
    ᷄
    0.44
     randomNumber
    0.44
     Nası
    0.43
     sigurn
    0.43
     Toxicol
    0.43
     görü
    0.42
     vill
    0.42
    怵
    0.42
    POSITIVE LOGITS
     cheaper
    0.98
    节省
    0.97
     efficiencies
    0.96
    reduce
    0.95
     reducing
    0.95
     reduce
    0.93
     frugal
    0.91
    reducing
    0.90
     efficient
    0.89
    efficient
    0.89
    Activations Density 0.266%

    No Known Activations