© 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. 99955
    Prev
    Next
    INDEX
    Explanations

    earn commission

    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
    予算
    -0.93
    valuate
    -0.83
     oferta
    -0.82
     idade
    -0.81
    预算
    -0.80
    penup
    -0.80
    ALLENGE
    -0.79
     değer
    -0.79
     оценки
    -0.79
    áreas
    -0.78
    POSITIVE LOGITS
     royalty
    2.34
     percentage
    2.25
     royalties
    2.16
     share
    1.95
     percentages
    1.90
    share
    1.66
     percent
    1.65
    percentage
    1.65
     porcentaje
    1.55
     commission
    1.52
    Activations Density 0.032%

    No Known Activations