© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90083
    Prev
    Next
    INDEX
    Explanations

    generated by code

    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
    вится
    -0.92
    வா
    -0.87
    uggest
    -0.86
    
    -0.86
    chtest
    -0.86
     Ordo
    -0.84
    rát
    -0.84
    ClCompile
    -0.84
     Harvesting
    -0.83
    無し
    -0.83
    POSITIVE LOGITS
     by
    1.83
     with
    1.05
     bởi
    1.04
     for
    1.02
     according
    0.95
     Da
    0.88
     based
    0.88
     з
    0.85
     By
    0.85
     по
    0.82
    Activations Density 0.009%

    No Known Activations