© 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. 111000
    Prev
    Next
    INDEX
    Explanations

    quantities and their relationships

    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
     and
    -1.31
    besides
    -1.00
    
    -1.00
    mathbf
    -0.99
    ificantly
    -0.98
     mög
    -0.98
     fatiga
    -0.96
    ranging
    -0.96
    ntax
    -0.96
    emand
    -0.96
    POSITIVE LOGITS
     of
    5.19
     that
    1.90
     at
    1.36
     for
    1.33
     you
    1.27
    りましたが
    1.21
     dicha
    1.09
     needed
    1.06
    それでも
    1.05
     των
    1.03
    Activations Density 0.135%

    No Known Activations