© 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. 32838
    Prev
    Next
    INDEX
    Explanations

    official documents and policy implementation

    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
    (--
    -0.83
    hae
    -0.81
     spf
    -0.80
    ﻛ
    -0.79
    瑋
    -0.77
     Tämä
    -0.75
     nunc
    -0.75
    صفات
    -0.74
    hender
    -0.73
     WING
    -0.73
    POSITIVE LOGITS
    《
    1.02
     Measures
    0.91
     document
    0.90
     Work
    0.89
     policy
    0.89
     implementation
    0.83
    Opinions
    0.82
    ఞ
    0.81
    restler
    0.79
     Measure
    0.78
    Activations Density 0.013%

    No Known Activations