© 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. 37973
    Prev
    Next
    INDEX
    Explanations

    comparisons and questions about kinds

    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
     where
    -1.06
     only
    -1.05
     closer
    -0.98
    ても
    -0.98
     uses
    -0.98
     torebka
    -0.94
    gunakan
    -0.94
    ....
    -0.93
     proves
    -0.93
     and
    -0.92
    POSITIVE LOGITS
     http
    1.42
     ought
    1.37
     https
    1.34
     nonetheless
    1.24
    \&
    1.21
     pourraient
    1.20
    
    
    1.18
    1.18
    ()
    
    1.17
    =[]
    1.16
    Activations Density 0.605%

    No Known Activations