© 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. 107505
    Prev
    Next
    INDEX
    Explanations

    a central

    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
    diging
    -0.96
    ETIME
    -0.91
    extField
    -0.85
    ared
    -0.85
    cshtml
    -0.85
     simultaneous
    -0.84
    チーム
    -0.84
    тті
    -0.83
    lovely
    -0.82
    ኹ
    -0.82
    POSITIVE LOGITS
     central
    1.68
    central
    1.32
     Central
    1.27
     gateway
    1.21
     centralized
    1.13
    Central
    1.12
     concentr
    1.09
     master
    1.05
     management
    1.02
     центра
    1.02
    Activations Density 0.250%

    No Known Activations