© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119225
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames/titles

    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
    낙
    -0.90
    сение
    -0.81
    Kilde
    -0.78
    Osob
    -0.76
    hould
    -0.75
     setError
    -0.75
    =_
    -0.74
    Och
    -0.73
     ブレスレット
    -0.73
    vité
    -0.73
    POSITIVE LOGITS
    HRM
    1.20
     HRM
    1.08
    Management
    1.06
     management
    1.02
     managerial
    0.98
     Management
    0.96
     organisational
    0.96
     MANAGEMENT
    0.92
    MANAGEMENT
    0.88
    lceil
    0.88
    Activations Density 0.018%

    No Known Activations